Time Series Forecasting
Transformers
Safetensors
Timer-S1
time series
time-series
forecasting
foundation models
pretrained models
time series foundation models
custom_code
Instructions to use bytedance-research/Timer-S1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use bytedance-research/Timer-S1 with Transformers:
# Load model directly from transformers import Timer-S1 model = Timer-S1.from_pretrained("bytedance-research/Timer-S1", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "metadata": { | |
| "total_size": 16607308352 | |
| }, | |
| "weight_map": { | |
| "model.embed_layer.hidden_layer.bias": "model-00001-of-00004.safetensors", | |
| "model.embed_layer.hidden_layer.weight": "model-00001-of-00004.safetensors", | |
| "model.embed_layer.output_layer.bias": "model-00001-of-00004.safetensors", | |
| "model.embed_layer.output_layer.weight": "model-00001-of-00004.safetensors", | |
| "model.embed_layer.residual_layer.bias": "model-00001-of-00004.safetensors", | |
| "model.embed_layer.residual_layer.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.0.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.0.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.0.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.1.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.1.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.1.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.10.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.10.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.10.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.11.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.11.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.11.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.12.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.12.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.12.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.13.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.13.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.13.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.14.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.14.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.14.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.15.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.15.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.15.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.16.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.16.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.16.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.17.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.17.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.17.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.18.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.18.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.18.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.19.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.19.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.19.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.2.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.2.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.2.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.20.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.20.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.20.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.21.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.21.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.21.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.22.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.22.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.22.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.23.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.23.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.23.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.24.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.24.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.24.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.25.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.25.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.25.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.26.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.26.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.26.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.27.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.27.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.27.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.28.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.28.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.28.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.29.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.29.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.29.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.3.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.3.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.3.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.30.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.30.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.30.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.31.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.31.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.31.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.4.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.4.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.4.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.5.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.5.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.5.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.6.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.6.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.6.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.7.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.7.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.7.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.8.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.8.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.8.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.9.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.9.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.experts.9.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.ffn_layer.gate.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.norm1.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.norm2.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.self_attn.gate_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.0.self_attn.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.self_attn.k_scale": "model-00001-of-00004.safetensors", | |
| "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.self_attn.q_scale": "model-00001-of-00004.safetensors", | |
| "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.0.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.0.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.0.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.1.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.1.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.1.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.10.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.10.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.10.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.11.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.11.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.11.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.12.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.12.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.12.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.13.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.13.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.13.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.14.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.14.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.14.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.15.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.15.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.15.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.16.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.16.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.16.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.17.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.17.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.17.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.18.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.18.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.18.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.19.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.19.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.19.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.2.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.2.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.2.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.20.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.20.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.20.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.21.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.21.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.21.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.22.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.22.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.22.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.23.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.23.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.23.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.24.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.24.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.24.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.25.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.25.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.25.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.26.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.26.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.26.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.27.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.27.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.27.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.28.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.28.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.28.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.29.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.29.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.29.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.3.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.3.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.3.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.30.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.30.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.30.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.31.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.31.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.31.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.4.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.4.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.4.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.5.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.5.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.5.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.6.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.6.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.6.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.7.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.7.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.7.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.8.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.8.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.8.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.9.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.9.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.experts.9.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.ffn_layer.gate.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.norm1.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.norm2.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.self_attn.gate_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.1.self_attn.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.self_attn.k_scale": "model-00001-of-00004.safetensors", | |
| "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.self_attn.q_scale": "model-00001-of-00004.safetensors", | |
| "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.0.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.0.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.0.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.1.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.1.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.1.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.10.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.10.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.10.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.11.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.11.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.11.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.12.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.12.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.12.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.13.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.13.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.13.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.14.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.14.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.14.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.15.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.15.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.15.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.16.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.16.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.16.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.17.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.17.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.17.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.18.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.18.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.18.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.19.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.19.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.19.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.2.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.2.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.2.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.20.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.20.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.20.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.21.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.21.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.21.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.22.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.22.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.22.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.23.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.23.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.23.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.24.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.24.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.24.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.25.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.25.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.25.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.26.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.26.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.26.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.27.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.27.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.27.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.28.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.28.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.28.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.29.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.29.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.29.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.3.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.3.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.3.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.30.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.30.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.30.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.31.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.31.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.31.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.4.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.4.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.4.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.5.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.5.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.5.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.6.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.6.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.6.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.7.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.7.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.7.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.8.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.8.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.8.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.9.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.9.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.experts.9.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.ffn_layer.gate.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.norm1.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.norm2.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.self_attn.gate_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.10.self_attn.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.self_attn.k_scale": "model-00001-of-00004.safetensors", | |
| "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.self_attn.q_scale": "model-00001-of-00004.safetensors", | |
| "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.0.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.0.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.0.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.1.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.1.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.1.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.10.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.10.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.10.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.11.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.11.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.11.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.12.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.12.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.12.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.13.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.13.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.13.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.14.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.14.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.14.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.15.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.15.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.15.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.16.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.16.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.16.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.17.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.17.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.17.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.18.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.18.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.18.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.19.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.19.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.19.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.2.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.2.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.2.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.20.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.20.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.20.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.21.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.21.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.21.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.22.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.22.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.22.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.23.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.23.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.23.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.24.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.24.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.24.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.25.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.25.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.25.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.26.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.26.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.26.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.27.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.27.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.27.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.28.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.28.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.28.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.29.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.29.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.29.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.3.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.3.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.3.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.30.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.30.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.30.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.31.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.31.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.31.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.4.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.4.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.4.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.5.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.5.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.5.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.6.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.6.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.6.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.7.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.7.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.7.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.8.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.8.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.8.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.9.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.9.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.experts.9.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.ffn_layer.gate.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.norm1.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.norm2.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.self_attn.gate_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.11.self_attn.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.self_attn.k_scale": "model-00001-of-00004.safetensors", | |
| "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.11.self_attn.q_scale": "model-00001-of-00004.safetensors", | |
| "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.0.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.0.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.0.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.1.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.1.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.1.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.10.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.10.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.10.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.11.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.11.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.11.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.12.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.12.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.12.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.13.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.13.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.13.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.14.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.14.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.14.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.15.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.15.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.15.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.16.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.16.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.16.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.17.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.17.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.17.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.18.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.18.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.18.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.19.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.19.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.19.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.2.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.2.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.2.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.20.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.20.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.20.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.21.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.21.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.21.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.22.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.22.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.22.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.23.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.23.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.23.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.24.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.24.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.24.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.25.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.25.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.25.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.26.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.26.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.26.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.27.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.27.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.27.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.28.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.28.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.28.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.29.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.29.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.29.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.3.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.3.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.3.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.30.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.30.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.30.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.31.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.31.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.31.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.4.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.4.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.4.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.5.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.5.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.5.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.6.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.6.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.6.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.7.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.7.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.7.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.8.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.8.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.8.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.9.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.9.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.experts.9.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.ffn_layer.gate.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.12.norm1.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.norm2.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.self_attn.gate_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.12.self_attn.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.12.self_attn.k_scale": "model-00001-of-00004.safetensors", | |
| "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.12.self_attn.q_scale": "model-00001-of-00004.safetensors", | |
| "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.0.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.0.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.0.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.1.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.1.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.1.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.10.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.10.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.10.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.11.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.11.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.11.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.12.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.12.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.12.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.13.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.13.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.13.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.14.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.14.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.14.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.15.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.15.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.15.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.16.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.16.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.16.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.17.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.17.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.17.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.18.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.18.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.18.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.19.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.19.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.19.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.2.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.2.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.2.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.20.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.20.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.20.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.21.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.21.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.21.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.22.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.22.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.22.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.23.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.23.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.23.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.24.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.24.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.24.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.25.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.25.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.25.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.26.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.26.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.26.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.27.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.27.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.27.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.28.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.28.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.28.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.29.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.29.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.29.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.3.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.3.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.3.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.30.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.30.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.30.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.31.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.31.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.31.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.4.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.4.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.4.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.5.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.5.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.5.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.6.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.6.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.6.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.7.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.7.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.7.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.8.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.8.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.8.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.9.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.9.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.experts.9.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.ffn_layer.gate.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.norm1.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.norm2.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.self_attn.gate_proj.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.13.self_attn.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.self_attn.k_scale": "model-00002-of-00004.safetensors", | |
| "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.self_attn.q_scale": "model-00002-of-00004.safetensors", | |
| "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.0.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.0.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.0.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.1.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.1.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.1.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.10.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.10.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.10.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.11.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.11.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.11.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.12.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.12.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.12.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.13.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.13.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.13.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.14.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.14.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.14.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.15.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.15.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.15.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.16.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.16.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.16.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.17.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.17.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.17.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.18.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.18.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.18.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.19.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.19.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.19.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.2.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.2.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.2.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.20.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.20.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.20.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.21.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.21.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.21.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.22.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.22.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.22.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.23.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.23.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.23.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.24.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.24.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.24.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.25.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.25.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.25.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.26.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.26.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.26.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.27.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.27.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.27.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.28.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.28.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.28.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.29.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.29.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.29.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.3.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.3.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.3.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.30.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.30.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.30.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.31.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.31.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.31.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.4.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.4.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.4.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.5.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.5.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.5.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.6.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.6.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.6.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.7.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.7.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.7.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.8.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.8.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.8.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.9.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.9.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.experts.9.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.ffn_layer.gate.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.norm1.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.norm2.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.self_attn.gate_proj.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.14.self_attn.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.self_attn.k_scale": "model-00002-of-00004.safetensors", | |
| "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.self_attn.q_scale": "model-00002-of-00004.safetensors", | |
| "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.0.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.0.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.0.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.1.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.1.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.1.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.10.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.10.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.10.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.11.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.11.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.11.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.12.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.12.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.12.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.13.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.13.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.13.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.14.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.14.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.14.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.15.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.15.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.15.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.16.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.16.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.16.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.17.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.17.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.17.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.18.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.18.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.18.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.19.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.19.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.19.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.2.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.2.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.2.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.20.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.20.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.20.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.21.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.21.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.21.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.22.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.22.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.22.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.23.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.23.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.23.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.24.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.24.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.24.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.25.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.25.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.25.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.26.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.26.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.26.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.27.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.27.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.27.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.28.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.28.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.28.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.29.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.29.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.29.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.3.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.3.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.3.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.30.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.30.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.30.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.31.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.31.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.31.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.4.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.4.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.4.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.5.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.5.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.5.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.6.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.6.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.6.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.7.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.7.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.7.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.8.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.8.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.8.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.9.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.9.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.experts.9.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.ffn_layer.gate.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.norm1.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.norm2.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.self_attn.gate_proj.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.15.self_attn.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.self_attn.k_scale": "model-00002-of-00004.safetensors", | |
| "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.self_attn.q_scale": "model-00002-of-00004.safetensors", | |
| "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.0.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.0.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.0.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.1.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.1.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.1.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.10.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.10.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.10.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.11.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.11.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.11.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.12.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.12.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.12.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.13.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.13.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.13.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.14.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.14.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.14.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.15.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.15.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.15.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.16.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.16.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.16.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.17.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.17.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.17.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.18.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.18.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.18.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.19.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.19.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.19.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.2.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.2.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.2.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.20.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.20.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.20.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.21.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.21.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.21.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.22.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.22.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.22.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.23.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.23.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.23.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.24.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.24.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.24.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.25.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.25.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.25.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.26.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.26.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.26.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.27.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.27.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.27.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.28.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.28.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.28.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.29.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.29.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.29.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.3.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.3.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.3.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.30.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.30.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.30.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.31.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.31.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.31.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.4.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.4.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.4.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.5.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.5.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.5.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.6.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.6.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.6.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.7.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.7.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.7.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.8.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.8.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.8.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.9.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.9.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.experts.9.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.ffn_layer.gate.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.norm1.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.norm2.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.self_attn.gate_proj.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.16.self_attn.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.self_attn.k_scale": "model-00002-of-00004.safetensors", | |
| "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.self_attn.q_scale": "model-00002-of-00004.safetensors", | |
| "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.0.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.0.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.0.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.1.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.1.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.1.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.10.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.10.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.10.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.11.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.11.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.11.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.12.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.12.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.12.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.13.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.13.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.13.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.14.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.14.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.14.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.15.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.15.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.15.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.16.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.16.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.16.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.17.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.17.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.17.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.18.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.18.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.18.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.19.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.19.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.19.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.2.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.2.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.2.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.20.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.20.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.20.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.21.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.21.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.21.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.22.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.22.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.22.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.23.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.23.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.23.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.24.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.24.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.24.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.25.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.25.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.25.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.26.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.26.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.26.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.27.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.27.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.27.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.28.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.28.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.28.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.29.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.29.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.29.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.3.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.3.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.3.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.30.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.30.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.30.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.31.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.31.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.31.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.4.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.4.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.4.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.5.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.5.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.5.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.6.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.6.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.6.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.7.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.7.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.7.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.8.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.8.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.8.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.9.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.9.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.experts.9.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.ffn_layer.gate.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.norm1.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.norm2.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.self_attn.gate_proj.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.17.self_attn.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.self_attn.k_scale": "model-00002-of-00004.safetensors", | |
| "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.self_attn.q_scale": "model-00002-of-00004.safetensors", | |
| "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.0.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.0.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.0.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.1.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.1.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.1.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.10.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.10.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.10.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.11.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.11.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.11.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.12.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.12.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.12.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.13.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.13.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.13.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.14.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.14.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.14.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.15.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.15.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.15.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.16.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.16.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.16.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.17.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.17.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.17.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.18.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.18.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.18.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.19.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.19.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.19.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.2.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.2.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.2.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.20.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.20.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.20.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.21.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.21.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.21.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.22.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.22.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.22.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.23.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.23.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.23.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.24.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.24.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.24.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.25.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.25.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.25.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.26.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.26.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.26.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.27.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.27.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.27.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.28.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.28.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.28.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.29.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.29.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.29.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.3.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.3.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.3.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.30.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.30.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.30.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.31.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.31.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.31.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.4.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.4.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.4.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.5.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.5.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.5.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.6.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.6.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.6.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.7.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.7.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.7.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.8.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.8.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.8.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.9.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.9.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.experts.9.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.ffn_layer.gate.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.norm1.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.norm2.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.self_attn.gate_proj.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.18.self_attn.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.self_attn.k_scale": "model-00002-of-00004.safetensors", | |
| "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.self_attn.q_scale": "model-00002-of-00004.safetensors", | |
| "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.0.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.0.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.0.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.1.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.1.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.1.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.10.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.10.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.10.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.11.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.11.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.11.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.12.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.12.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.12.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.13.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.13.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.13.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.14.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.14.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.14.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.15.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.15.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.15.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.16.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.16.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.16.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.17.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.17.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.17.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.18.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.18.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.18.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.19.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.19.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.19.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.2.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.2.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.2.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.20.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.20.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.20.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.21.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.21.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.21.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.22.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.22.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.22.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.23.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.23.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.23.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.24.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.24.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.24.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.25.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.25.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.25.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.26.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.26.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.26.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.27.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.27.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.27.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.28.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.28.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.28.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.29.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.29.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.29.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.3.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.3.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.3.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.30.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.30.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.30.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.31.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.31.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.31.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.4.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.4.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.4.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.5.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.5.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.5.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.6.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.6.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.6.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.7.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.7.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.7.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.8.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.8.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.8.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.9.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.9.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.experts.9.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.ffn_layer.gate.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.norm1.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.norm2.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.self_attn.gate_proj.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.19.self_attn.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.self_attn.k_scale": "model-00002-of-00004.safetensors", | |
| "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.self_attn.q_scale": "model-00002-of-00004.safetensors", | |
| "model.layers.19.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.0.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.0.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.0.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.1.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.1.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.1.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.10.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.10.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.10.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.11.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.11.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.11.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.12.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.12.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.12.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.13.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.13.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.13.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.14.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.14.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.14.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.15.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.15.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.15.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.16.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.16.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.16.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.17.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.17.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.17.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.18.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.18.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.18.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.19.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.19.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.19.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.2.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.2.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.2.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.20.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.20.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.20.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.21.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.21.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.21.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.22.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.22.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.22.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.23.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.23.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.23.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.24.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.24.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.24.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.25.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.25.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.25.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.26.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.26.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.26.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.27.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.27.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.27.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.28.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.28.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.28.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.29.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.29.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.29.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.3.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.3.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.3.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.30.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.30.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.30.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.31.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.31.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.31.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.4.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.4.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.4.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.5.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.5.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.5.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.6.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.6.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.6.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.7.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.7.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.7.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.8.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.8.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.8.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.9.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.9.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.experts.9.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.ffn_layer.gate.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.norm1.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.norm2.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.self_attn.gate_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.2.self_attn.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.self_attn.k_scale": "model-00001-of-00004.safetensors", | |
| "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.self_attn.q_scale": "model-00001-of-00004.safetensors", | |
| "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.0.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.0.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.0.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.1.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.1.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.1.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.10.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.10.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.10.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.11.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.11.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.11.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.12.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.12.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.12.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.13.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.13.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.13.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.14.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.14.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.14.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.15.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.15.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.15.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.16.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.16.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.16.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.17.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.17.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.17.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.18.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.18.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.18.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.19.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.19.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.19.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.2.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.2.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.2.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.20.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.20.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.20.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.21.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.21.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.21.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.22.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.22.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.22.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.23.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.23.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.23.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.24.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.24.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.24.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.25.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.25.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.25.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.26.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.26.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.26.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.27.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.27.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.27.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.28.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.28.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.28.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.29.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.29.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.29.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.3.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.3.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.3.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.30.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.30.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.30.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.31.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.31.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.31.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.4.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.4.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.4.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.5.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.5.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.5.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.6.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.6.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.6.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.7.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.7.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.7.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.8.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.8.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.8.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.9.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.9.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.experts.9.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.ffn_layer.gate.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.norm1.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.norm2.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.self_attn.gate_proj.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.20.self_attn.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.self_attn.k_scale": "model-00002-of-00004.safetensors", | |
| "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.20.self_attn.q_scale": "model-00002-of-00004.safetensors", | |
| "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.0.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.0.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.0.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.1.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.1.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.1.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.10.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.10.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.10.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.11.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.11.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.11.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.12.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.12.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.12.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.13.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.13.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.13.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.14.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.14.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.14.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.15.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.15.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.15.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.16.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.16.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.16.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.17.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.17.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.17.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.18.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.18.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.18.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.19.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.19.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.19.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.2.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.2.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.2.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.20.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.20.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.20.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.21.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.21.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.21.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.22.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.22.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.22.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.23.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.23.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.23.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.24.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.24.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.24.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.25.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.25.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.25.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.26.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.26.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.26.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.27.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.27.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.27.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.28.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.28.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.28.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.29.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.29.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.29.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.3.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.3.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.3.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.30.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.30.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.30.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.31.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.31.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.31.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.4.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.4.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.4.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.5.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.5.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.5.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.6.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.6.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.6.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.7.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.7.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.7.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.8.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.8.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.8.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.9.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.9.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.experts.9.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.ffn_layer.gate.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.norm1.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.norm2.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.self_attn.gate_proj.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.21.self_attn.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.self_attn.k_scale": "model-00002-of-00004.safetensors", | |
| "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.21.self_attn.q_scale": "model-00002-of-00004.safetensors", | |
| "model.layers.21.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.0.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.0.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.0.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.1.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.1.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.1.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.10.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.10.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.10.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.11.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.11.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.11.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.12.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.12.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.12.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.13.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.13.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.13.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.14.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.14.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.14.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.15.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.15.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.15.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.16.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.16.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.16.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.17.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.17.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.17.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.18.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.18.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.18.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.19.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.19.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.19.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.2.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.2.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.2.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.20.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.20.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.20.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.21.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.21.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.21.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.22.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.22.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.22.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.23.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.23.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.23.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.24.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.24.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.24.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.25.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.25.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.25.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.26.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.26.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.26.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.27.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.27.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.27.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.28.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.28.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.28.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.29.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.29.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.29.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.3.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.3.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.3.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.30.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.30.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.30.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.31.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.31.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.31.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.4.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.4.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.4.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.5.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.5.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.5.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.6.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.6.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.6.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.7.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.7.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.7.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.8.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.8.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.8.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.9.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.9.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.experts.9.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.ffn_layer.gate.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.norm1.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.norm2.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.self_attn.gate_proj.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.22.self_attn.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.self_attn.k_scale": "model-00002-of-00004.safetensors", | |
| "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.22.self_attn.q_scale": "model-00002-of-00004.safetensors", | |
| "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.0.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.0.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.0.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.1.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.1.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.1.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.10.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.10.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.10.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.11.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.11.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.11.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.12.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.12.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.12.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.13.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.13.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.13.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.14.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.14.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.14.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.15.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.15.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.15.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.16.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.16.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.16.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.17.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.17.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.17.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.18.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.18.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.18.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.19.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.19.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.19.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.2.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.2.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.2.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.20.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.20.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.20.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.21.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.21.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.21.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.22.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.22.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.22.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.23.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.23.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.23.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.24.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.24.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.24.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.25.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.25.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.25.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.26.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.26.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.26.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.27.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.27.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.27.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.28.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.28.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.28.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.29.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.29.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.29.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.3.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.3.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.3.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.30.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.30.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.30.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.31.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.31.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.31.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.4.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.4.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.4.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.5.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.5.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.5.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.6.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.6.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.6.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.7.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.7.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.7.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.8.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.8.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.8.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.9.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.9.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.experts.9.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.ffn_layer.gate.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.norm1.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.norm2.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.self_attn.gate_proj.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.23.self_attn.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.self_attn.k_scale": "model-00002-of-00004.safetensors", | |
| "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.23.self_attn.q_scale": "model-00002-of-00004.safetensors", | |
| "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.0.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.0.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.0.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.1.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.1.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.1.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.10.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.10.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.10.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.11.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.11.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.11.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.12.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.12.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.12.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.13.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.13.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.13.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.14.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.14.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.14.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.15.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.15.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.15.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.16.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.16.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.16.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.17.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.17.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.17.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.18.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.18.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.18.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.19.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.19.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.19.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.2.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.2.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.2.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.20.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.20.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.20.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.21.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.21.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.21.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.22.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.22.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.22.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.23.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.23.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.23.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.24.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.24.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.24.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.25.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.25.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.25.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.26.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.26.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.26.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.27.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.27.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.27.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.28.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.28.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.28.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.29.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.29.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.29.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.3.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.3.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.3.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.30.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.30.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.30.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.31.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.31.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.31.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.4.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.4.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.4.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.5.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.5.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.5.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.6.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.6.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.6.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.7.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.7.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.7.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.8.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.8.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.8.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.9.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.9.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.experts.9.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.ffn_layer.gate.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.norm1.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.norm2.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.self_attn.gate_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.3.self_attn.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.self_attn.k_scale": "model-00001-of-00004.safetensors", | |
| "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.self_attn.q_scale": "model-00001-of-00004.safetensors", | |
| "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.0.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.0.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.0.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.1.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.1.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.1.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.10.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.10.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.10.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.11.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.11.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.11.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.12.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.12.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.12.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.13.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.13.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.13.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.14.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.14.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.14.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.15.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.15.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.15.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.16.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.16.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.16.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.17.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.17.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.17.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.18.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.18.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.18.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.19.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.19.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.19.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.2.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.2.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.2.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.20.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.20.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.20.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.21.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.21.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.21.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.22.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.22.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.22.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.23.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.23.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.23.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.24.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.24.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.24.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.25.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.25.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.25.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.26.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.26.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.26.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.27.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.27.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.27.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.28.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.28.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.28.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.29.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.29.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.29.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.3.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.3.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.3.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.30.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.30.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.30.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.31.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.31.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.31.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.4.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.4.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.4.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.5.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.5.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.5.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.6.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.6.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.6.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.7.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.7.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.7.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.8.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.8.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.8.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.9.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.9.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.experts.9.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.ffn_layer.gate.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.norm1.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.norm2.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.self_attn.gate_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.4.self_attn.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.self_attn.k_scale": "model-00001-of-00004.safetensors", | |
| "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.self_attn.q_scale": "model-00001-of-00004.safetensors", | |
| "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.0.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.0.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.0.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.1.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.1.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.1.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.10.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.10.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.10.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.11.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.11.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.11.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.12.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.12.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.12.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.13.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.13.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.13.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.14.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.14.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.14.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.15.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.15.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.15.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.16.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.16.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.16.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.17.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.17.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.17.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.18.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.18.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.18.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.19.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.19.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.19.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.2.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.2.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.2.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.20.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.20.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.20.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.21.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.21.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.21.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.22.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.22.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.22.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.23.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.23.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.23.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.24.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.24.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.24.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.25.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.25.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.25.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.26.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.26.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.26.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.27.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.27.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.27.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.28.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.28.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.28.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.29.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.29.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.29.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.3.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.3.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.3.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.30.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.30.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.30.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.31.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.31.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.31.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.4.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.4.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.4.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.5.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.5.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.5.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.6.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.6.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.6.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.7.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.7.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.7.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.8.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.8.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.8.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.9.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.9.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.experts.9.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.ffn_layer.gate.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.norm1.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.norm2.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.self_attn.gate_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.5.self_attn.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.self_attn.k_scale": "model-00001-of-00004.safetensors", | |
| "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.self_attn.q_scale": "model-00001-of-00004.safetensors", | |
| "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.0.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.0.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.0.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.1.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.1.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.1.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.10.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.10.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.10.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.11.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.11.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.11.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.12.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.12.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.12.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.13.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.13.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.13.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.14.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.14.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.14.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.15.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.15.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.15.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.16.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.16.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.16.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.17.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.17.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.17.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.18.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.18.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.18.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.19.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.19.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.19.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.2.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.2.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.2.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.20.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.20.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.20.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.21.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.21.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.21.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.22.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.22.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.22.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.23.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.23.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.23.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.24.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.24.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.24.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.25.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.25.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.25.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.26.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.26.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.26.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.27.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.27.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.27.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.28.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.28.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.28.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.29.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.29.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.29.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.3.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.3.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.3.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.30.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.30.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.30.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.31.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.31.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.31.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.4.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.4.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.4.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.5.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.5.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.5.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.6.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.6.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.6.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.7.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.7.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.7.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.8.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.8.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.8.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.9.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.9.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.experts.9.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.ffn_layer.gate.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.norm1.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.norm2.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.self_attn.gate_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.6.self_attn.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.self_attn.k_scale": "model-00001-of-00004.safetensors", | |
| "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.self_attn.q_scale": "model-00001-of-00004.safetensors", | |
| "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.0.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.0.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.0.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.1.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.1.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.1.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.10.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.10.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.10.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.11.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.11.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.11.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.12.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.12.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.12.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.13.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.13.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.13.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.14.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.14.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.14.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.15.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.15.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.15.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.16.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.16.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.16.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.17.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.17.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.17.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.18.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.18.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.18.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.19.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.19.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.19.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.2.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.2.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.2.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.20.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.20.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.20.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.21.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.21.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.21.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.22.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.22.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.22.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.23.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.23.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.23.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.24.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.24.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.24.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.25.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.25.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.25.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.26.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.26.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.26.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.27.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.27.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.27.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.28.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.28.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.28.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.29.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.29.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.29.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.3.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.3.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.3.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.30.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.30.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.30.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.31.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.31.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.31.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.4.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.4.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.4.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.5.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.5.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.5.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.6.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.6.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.6.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.7.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.7.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.7.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.8.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.8.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.8.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.9.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.9.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.experts.9.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.ffn_layer.gate.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.norm1.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.norm2.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.self_attn.gate_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.7.self_attn.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.self_attn.k_scale": "model-00001-of-00004.safetensors", | |
| "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.self_attn.q_scale": "model-00001-of-00004.safetensors", | |
| "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.0.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.0.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.0.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.1.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.1.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.1.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.10.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.10.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.10.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.11.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.11.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.11.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.12.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.12.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.12.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.13.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.13.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.13.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.14.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.14.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.14.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.15.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.15.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.15.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.16.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.16.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.16.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.17.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.17.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.17.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.18.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.18.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.18.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.19.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.19.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.19.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.2.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.2.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.2.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.20.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.20.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.20.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.21.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.21.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.21.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.22.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.22.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.22.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.23.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.23.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.23.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.24.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.24.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.24.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.25.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.25.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.25.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.26.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.26.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.26.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.27.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.27.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.27.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.28.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.28.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.28.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.29.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.29.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.29.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.3.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.3.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.3.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.30.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.30.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.30.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.31.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.31.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.31.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.4.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.4.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.4.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.5.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.5.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.5.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.6.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.6.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.6.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.7.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.7.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.7.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.8.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.8.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.8.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.9.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.9.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.experts.9.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.ffn_layer.gate.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.norm1.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.norm2.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.self_attn.gate_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.8.self_attn.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.self_attn.k_scale": "model-00001-of-00004.safetensors", | |
| "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.self_attn.q_scale": "model-00001-of-00004.safetensors", | |
| "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.0.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.0.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.0.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.1.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.1.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.1.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.10.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.10.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.10.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.11.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.11.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.11.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.12.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.12.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.12.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.13.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.13.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.13.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.14.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.14.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.14.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.15.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.15.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.15.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.16.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.16.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.16.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.17.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.17.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.17.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.18.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.18.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.18.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.19.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.19.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.19.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.2.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.2.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.2.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.20.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.20.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.20.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.21.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.21.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.21.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.22.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.22.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.22.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.23.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.23.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.23.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.24.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.24.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.24.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.25.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.25.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.25.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.26.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.26.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.26.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.27.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.27.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.27.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.28.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.28.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.28.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.29.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.29.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.29.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.3.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.3.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.3.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.30.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.30.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.30.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.31.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.31.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.31.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.4.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.4.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.4.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.5.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.5.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.5.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.6.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.6.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.6.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.7.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.7.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.7.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.8.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.8.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.8.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.9.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.9.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.experts.9.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.ffn_layer.gate.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.norm1.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.norm2.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.self_attn.gate_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.9.self_attn.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.self_attn.k_scale": "model-00001-of-00004.safetensors", | |
| "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.self_attn.q_scale": "model-00001-of-00004.safetensors", | |
| "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.norm.weight": "model-00002-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.0.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.0.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.0.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.1.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.1.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.1.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.10.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.10.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.10.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.11.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.11.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.11.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.12.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.12.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.12.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.13.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.13.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.13.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.14.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.14.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.14.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.15.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.15.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.15.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.16.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.16.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.16.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.17.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.17.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.17.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.18.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.18.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.18.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.19.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.19.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.19.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.2.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.2.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.2.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.20.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.20.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.20.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.21.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.21.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.21.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.22.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.22.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.22.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.23.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.23.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.23.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.24.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.24.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.24.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.25.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.25.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.25.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.26.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.26.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.26.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.27.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.27.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.27.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.28.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.28.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.28.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.29.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.29.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.29.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.3.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.3.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.3.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.30.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.30.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.30.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.31.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.31.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.31.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.4.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.4.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.4.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.5.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.5.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.5.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.6.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.6.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.6.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.7.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.7.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.7.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.8.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.8.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.8.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.9.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.9.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.experts.9.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.ffn_layer.gate.weight": "model-00002-of-00004.safetensors", | |
| "mtp_modules.0.layer.norm1.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.norm2.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.layer.self_attn.gate_proj.bias": "model-00002-of-00004.safetensors", | |
| "mtp_modules.0.layer.self_attn.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "mtp_modules.0.layer.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", | |
| "mtp_modules.0.layer.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", | |
| "mtp_modules.0.layer.self_attn.k_scale": "model-00002-of-00004.safetensors", | |
| "mtp_modules.0.layer.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", | |
| "mtp_modules.0.layer.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", | |
| "mtp_modules.0.layer.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", | |
| "mtp_modules.0.layer.self_attn.q_scale": "model-00002-of-00004.safetensors", | |
| "mtp_modules.0.layer.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", | |
| "mtp_modules.0.layer.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", | |
| "mtp_modules.0.norm.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.0.norm_embeds.weight": "model-00002-of-00004.safetensors", | |
| "mtp_modules.0.norm_hidden.weight": "model-00002-of-00004.safetensors", | |
| "mtp_modules.0.projection_matrix.weight": "model-00002-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.0.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.0.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.0.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.1.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.1.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.1.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.10.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.10.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.10.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.11.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.11.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.11.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.12.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.12.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.12.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.13.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.13.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.13.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.14.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.14.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.14.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.15.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.15.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.15.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.16.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.16.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.16.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.17.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.17.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.17.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.18.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.18.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.18.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.19.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.19.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.19.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.2.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.2.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.2.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.20.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.20.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.20.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.21.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.21.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.21.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.22.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.22.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.22.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.23.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.23.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.23.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.24.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.24.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.24.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.25.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.25.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.25.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.26.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.26.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.26.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.27.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.27.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.27.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.28.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.28.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.28.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.29.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.29.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.29.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.3.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.3.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.3.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.30.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.30.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.30.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.31.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.31.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.31.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.4.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.4.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.4.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.5.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.5.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.5.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.6.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.6.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.6.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.7.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.7.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.7.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.8.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.8.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.8.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.9.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.9.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.experts.9.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.ffn_layer.gate.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.norm1.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.norm2.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.self_attn.gate_proj.bias": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.self_attn.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.self_attn.k_scale": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.self_attn.q_scale": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.layer.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.norm.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.norm_embeds.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.norm_hidden.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.1.projection_matrix.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.0.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.0.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.0.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.1.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.1.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.1.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.10.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.10.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.10.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.11.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.11.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.11.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.12.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.12.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.12.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.13.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.13.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.13.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.14.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.14.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.14.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.15.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.15.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.15.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.16.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.16.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.16.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.17.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.17.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.17.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.18.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.18.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.18.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.19.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.19.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.19.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.2.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.2.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.2.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.20.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.20.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.20.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.21.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.21.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.21.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.22.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.22.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.22.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.23.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.23.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.23.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.24.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.24.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.24.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.25.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.25.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.25.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.26.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.26.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.26.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.27.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.27.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.27.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.28.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.28.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.28.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.29.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.29.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.29.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.3.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.3.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.3.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.30.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.30.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.30.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.31.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.31.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.31.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.4.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.4.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.4.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.5.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.5.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.5.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.6.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.6.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.6.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.7.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.7.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.7.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.8.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.8.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.8.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.9.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.9.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.experts.9.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.ffn_layer.gate.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.norm1.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.norm2.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.self_attn.gate_proj.bias": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.self_attn.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.self_attn.k_scale": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.self_attn.q_scale": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.layer.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.norm.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.norm_embeds.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.norm_hidden.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.10.projection_matrix.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.0.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.0.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.0.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.1.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.1.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.1.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.10.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.10.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.10.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.11.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.11.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.11.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.12.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.12.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.12.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.13.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.13.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.13.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.14.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.14.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.14.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.15.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.15.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.15.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.16.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.16.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.16.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.17.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.17.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.17.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.18.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.18.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.18.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.19.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.19.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.19.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.2.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.2.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.2.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.20.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.20.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.20.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.21.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.21.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.21.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.22.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.22.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.22.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.23.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.23.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.23.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.24.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.24.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.24.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.25.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.25.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.25.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.26.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.26.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.26.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.27.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.27.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.27.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.28.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.28.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.28.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.29.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.29.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.29.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.3.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.3.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.3.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.30.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.30.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.30.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.31.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.31.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.31.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.4.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.4.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.4.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.5.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.5.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.5.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.6.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.6.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.6.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.7.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.7.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.7.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.8.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.8.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.8.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.9.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.9.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.experts.9.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.ffn_layer.gate.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.norm1.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.norm2.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.self_attn.gate_proj.bias": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.self_attn.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.self_attn.k_scale": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.self_attn.q_scale": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.layer.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.norm.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.norm_embeds.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.norm_hidden.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.11.projection_matrix.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.0.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.0.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.0.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.1.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.1.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.1.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.10.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.10.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.10.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.11.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.11.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.11.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.12.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.12.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.12.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.13.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.13.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.13.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.14.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.14.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.14.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.15.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.15.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.15.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.16.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.16.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.16.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.17.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.17.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.17.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.18.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.18.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.18.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.19.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.19.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.19.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.2.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.2.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.2.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.20.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.20.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.20.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.21.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.21.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.21.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.22.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.22.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.22.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.23.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.23.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.23.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.24.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.24.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.24.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.25.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.25.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.25.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.26.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.26.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.26.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.27.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.27.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.27.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.28.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.28.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.28.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.29.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.29.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.29.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.3.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.3.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.3.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.30.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.30.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.30.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.31.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.31.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.31.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.4.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.4.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.4.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.5.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.5.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.5.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.6.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.6.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.6.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.7.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.7.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.7.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.8.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.8.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.8.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.9.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.9.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.experts.9.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.ffn_layer.gate.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.12.layer.norm1.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.norm2.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.layer.self_attn.gate_proj.bias": "model-00003-of-00004.safetensors", | |
| "mtp_modules.12.layer.self_attn.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.12.layer.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", | |
| "mtp_modules.12.layer.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.12.layer.self_attn.k_scale": "model-00003-of-00004.safetensors", | |
| "mtp_modules.12.layer.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.12.layer.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", | |
| "mtp_modules.12.layer.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.12.layer.self_attn.q_scale": "model-00003-of-00004.safetensors", | |
| "mtp_modules.12.layer.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", | |
| "mtp_modules.12.layer.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.12.norm.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.12.norm_embeds.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.12.norm_hidden.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.12.projection_matrix.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.0.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.0.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.0.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.1.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.1.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.1.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.10.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.10.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.10.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.11.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.11.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.11.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.12.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.12.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.12.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.13.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.13.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.13.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.14.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.14.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.14.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.15.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.15.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.15.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.16.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.16.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.16.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.17.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.17.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.17.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.18.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.18.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.18.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.19.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.19.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.19.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.2.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.2.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.2.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.20.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.20.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.20.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.21.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.21.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.21.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.22.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.22.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.22.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.23.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.23.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.23.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.24.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.24.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.24.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.25.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.25.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.25.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.26.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.26.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.26.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.27.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.27.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.27.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.28.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.28.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.28.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.29.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.29.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.29.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.3.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.3.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.3.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.30.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.30.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.30.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.31.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.31.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.31.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.4.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.4.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.4.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.5.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.5.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.5.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.6.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.6.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.6.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.7.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.7.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.7.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.8.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.8.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.8.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.9.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.9.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.experts.9.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.ffn_layer.gate.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.norm1.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.norm2.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.self_attn.gate_proj.bias": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.self_attn.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.self_attn.k_proj.bias": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.self_attn.k_scale": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.self_attn.q_proj.bias": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.self_attn.q_scale": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.self_attn.v_proj.bias": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.layer.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.norm.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.norm_embeds.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.norm_hidden.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.13.projection_matrix.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.0.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.0.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.0.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.1.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.1.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.1.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.10.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.10.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.10.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.11.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.11.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.11.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.12.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.12.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.12.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.13.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.13.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.13.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.14.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.14.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.14.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.15.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.15.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.15.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.16.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.16.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.16.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.17.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.17.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.17.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.18.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.18.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.18.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.19.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.19.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.19.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.2.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.2.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.2.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.20.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.20.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.20.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.21.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.21.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.21.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.22.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.22.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.22.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.23.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.23.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.23.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.24.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.24.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.24.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.25.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.25.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.25.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.26.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.26.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.26.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.27.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.27.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.27.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.28.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.28.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.28.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.29.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.29.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.29.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.3.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.3.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.3.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.30.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.30.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.30.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.31.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.31.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.31.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.4.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.4.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.4.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.5.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.5.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.5.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.6.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.6.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.6.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.7.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.7.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.7.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.8.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.8.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.8.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.9.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.9.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.experts.9.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.ffn_layer.gate.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.norm1.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.norm2.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.self_attn.gate_proj.bias": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.self_attn.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.self_attn.k_proj.bias": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.self_attn.k_scale": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.self_attn.q_proj.bias": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.self_attn.q_scale": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.self_attn.v_proj.bias": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.layer.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.norm.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.norm_embeds.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.norm_hidden.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.14.projection_matrix.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.0.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.0.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.0.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.1.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.1.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.1.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.10.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.10.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.10.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.11.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.11.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.11.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.12.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.12.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.12.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.13.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.13.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.13.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.14.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.14.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.14.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.15.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.15.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.15.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.16.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.16.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.16.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.17.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.17.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.17.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.18.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.18.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.18.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.19.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.19.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.19.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.2.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.2.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.2.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.20.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.20.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.20.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.21.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.21.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.21.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.22.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.22.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.22.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.23.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.23.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.23.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.24.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.24.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.24.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.25.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.25.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.25.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.26.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.26.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.26.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.27.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.27.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.27.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.28.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.28.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.28.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.29.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.29.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.29.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.3.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.3.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.3.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.30.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.30.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.30.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.31.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.31.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.31.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.4.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.4.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.4.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.5.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.5.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.5.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.6.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.6.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.6.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.7.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.7.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.7.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.8.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.8.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.8.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.9.down_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.9.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.experts.9.up_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.ffn_layer.gate.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.norm1.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.norm2.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.self_attn.gate_proj.bias": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.self_attn.gate_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.self_attn.k_proj.bias": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.self_attn.k_scale": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.self_attn.q_proj.bias": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.self_attn.q_scale": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.self_attn.v_proj.bias": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.layer.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.norm.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.norm_embeds.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.norm_hidden.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.15.projection_matrix.weight": "model-00004-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.0.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.0.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.0.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.1.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.1.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.1.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.10.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.10.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.10.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.11.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.11.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.11.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.12.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.12.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.12.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.13.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.13.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.13.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.14.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.14.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.14.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.15.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.15.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.15.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.16.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.16.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.16.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.17.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.17.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.17.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.18.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.18.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.18.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.19.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.19.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.19.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.2.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.2.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.2.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.20.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.20.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.20.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.21.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.21.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.21.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.22.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.22.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.22.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.23.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.23.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.23.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.24.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.24.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.24.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.25.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.25.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.25.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.26.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.26.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.26.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.27.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.27.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.27.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.28.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.28.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.28.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.29.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.29.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.29.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.3.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.3.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.3.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.30.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.30.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.30.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.31.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.31.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.31.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.4.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.4.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.4.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.5.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.5.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.5.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.6.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.6.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.6.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.7.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.7.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.7.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.8.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.8.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.8.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.9.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.9.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.experts.9.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.ffn_layer.gate.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.norm1.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.norm2.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.self_attn.gate_proj.bias": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.self_attn.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.self_attn.k_scale": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.self_attn.q_scale": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.layer.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.norm.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.norm_embeds.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.norm_hidden.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.2.projection_matrix.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.0.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.0.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.0.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.1.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.1.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.1.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.10.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.10.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.10.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.11.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.11.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.11.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.12.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.12.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.12.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.13.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.13.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.13.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.14.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.14.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.14.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.15.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.15.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.15.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.16.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.16.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.16.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.17.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.17.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.17.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.18.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.18.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.18.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.19.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.19.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.19.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.2.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.2.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.2.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.20.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.20.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.20.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.21.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.21.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.21.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.22.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.22.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.22.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.23.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.23.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.23.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.24.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.24.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.24.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.25.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.25.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.25.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.26.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.26.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.26.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.27.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.27.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.27.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.28.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.28.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.28.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.29.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.29.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.29.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.3.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.3.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.3.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.30.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.30.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.30.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.31.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.31.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.31.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.4.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.4.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.4.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.5.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.5.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.5.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.6.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.6.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.6.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.7.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.7.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.7.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.8.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.8.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.8.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.9.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.9.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.experts.9.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.ffn_layer.gate.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.norm1.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.norm2.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.self_attn.gate_proj.bias": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.self_attn.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.self_attn.k_scale": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.self_attn.q_scale": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.layer.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.norm.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.norm_embeds.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.norm_hidden.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.3.projection_matrix.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.0.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.0.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.0.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.1.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.1.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.1.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.10.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.10.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.10.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.11.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.11.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.11.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.12.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.12.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.12.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.13.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.13.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.13.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.14.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.14.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.14.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.15.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.15.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.15.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.16.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.16.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.16.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.17.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.17.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.17.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.18.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.18.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.18.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.19.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.19.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.19.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.2.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.2.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.2.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.20.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.20.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.20.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.21.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.21.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.21.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.22.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.22.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.22.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.23.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.23.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.23.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.24.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.24.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.24.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.25.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.25.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.25.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.26.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.26.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.26.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.27.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.27.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.27.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.28.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.28.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.28.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.29.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.29.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.29.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.3.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.3.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.3.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.30.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.30.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.30.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.31.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.31.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.31.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.4.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.4.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.4.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.5.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.5.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.5.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.6.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.6.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.6.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.7.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.7.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.7.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.8.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.8.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.8.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.9.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.9.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.experts.9.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.ffn_layer.gate.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.norm1.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.norm2.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.self_attn.gate_proj.bias": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.self_attn.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.self_attn.k_scale": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.self_attn.q_scale": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.layer.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.norm.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.norm_embeds.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.norm_hidden.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.4.projection_matrix.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.0.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.0.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.0.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.1.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.1.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.1.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.10.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.10.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.10.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.11.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.11.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.11.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.12.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.12.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.12.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.13.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.13.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.13.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.14.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.14.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.14.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.15.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.15.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.15.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.16.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.16.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.16.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.17.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.17.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.17.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.18.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.18.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.18.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.19.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.19.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.19.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.2.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.2.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.2.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.20.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.20.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.20.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.21.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.21.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.21.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.22.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.22.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.22.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.23.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.23.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.23.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.24.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.24.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.24.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.25.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.25.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.25.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.26.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.26.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.26.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.27.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.27.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.27.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.28.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.28.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.28.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.29.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.29.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.29.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.3.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.3.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.3.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.30.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.30.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.30.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.31.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.31.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.31.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.4.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.4.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.4.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.5.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.5.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.5.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.6.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.6.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.6.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.7.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.7.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.7.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.8.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.8.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.8.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.9.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.9.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.experts.9.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.ffn_layer.gate.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.norm1.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.norm2.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.self_attn.gate_proj.bias": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.self_attn.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.self_attn.k_scale": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.self_attn.q_scale": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.layer.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.norm.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.norm_embeds.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.norm_hidden.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.5.projection_matrix.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.0.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.0.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.0.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.1.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.1.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.1.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.10.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.10.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.10.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.11.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.11.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.11.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.12.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.12.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.12.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.13.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.13.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.13.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.14.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.14.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.14.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.15.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.15.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.15.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.16.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.16.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.16.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.17.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.17.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.17.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.18.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.18.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.18.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.19.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.19.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.19.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.2.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.2.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.2.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.20.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.20.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.20.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.21.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.21.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.21.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.22.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.22.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.22.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.23.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.23.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.23.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.24.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.24.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.24.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.25.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.25.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.25.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.26.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.26.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.26.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.27.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.27.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.27.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.28.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.28.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.28.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.29.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.29.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.29.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.3.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.3.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.3.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.30.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.30.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.30.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.31.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.31.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.31.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.4.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.4.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.4.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.5.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.5.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.5.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.6.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.6.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.6.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.7.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.7.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.7.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.8.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.8.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.8.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.9.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.9.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.experts.9.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.ffn_layer.gate.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.norm1.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.norm2.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.self_attn.gate_proj.bias": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.self_attn.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.self_attn.k_scale": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.self_attn.q_scale": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.layer.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.norm.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.norm_embeds.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.norm_hidden.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.6.projection_matrix.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.0.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.0.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.0.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.1.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.1.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.1.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.10.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.10.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.10.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.11.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.11.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.11.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.12.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.12.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.12.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.13.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.13.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.13.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.14.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.14.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.14.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.15.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.15.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.15.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.16.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.16.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.16.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.17.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.17.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.17.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.18.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.18.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.18.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.19.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.19.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.19.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.2.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.2.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.2.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.20.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.20.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.20.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.21.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.21.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.21.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.22.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.22.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.22.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.23.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.23.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.23.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.24.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.24.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.24.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.25.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.25.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.25.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.26.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.26.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.26.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.27.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.27.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.27.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.28.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.28.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.28.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.29.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.29.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.29.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.3.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.3.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.3.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.30.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.30.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.30.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.31.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.31.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.31.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.4.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.4.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.4.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.5.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.5.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.5.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.6.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.6.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.6.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.7.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.7.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.7.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.8.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.8.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.8.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.9.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.9.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.experts.9.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.ffn_layer.gate.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.norm1.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.norm2.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.self_attn.gate_proj.bias": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.self_attn.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.self_attn.k_scale": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.self_attn.q_scale": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.layer.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.norm.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.norm_embeds.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.norm_hidden.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.7.projection_matrix.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.0.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.0.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.0.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.1.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.1.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.1.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.10.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.10.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.10.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.11.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.11.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.11.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.12.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.12.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.12.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.13.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.13.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.13.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.14.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.14.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.14.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.15.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.15.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.15.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.16.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.16.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.16.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.17.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.17.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.17.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.18.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.18.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.18.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.19.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.19.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.19.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.2.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.2.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.2.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.20.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.20.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.20.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.21.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.21.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.21.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.22.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.22.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.22.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.23.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.23.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.23.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.24.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.24.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.24.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.25.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.25.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.25.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.26.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.26.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.26.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.27.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.27.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.27.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.28.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.28.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.28.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.29.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.29.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.29.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.3.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.3.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.3.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.30.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.30.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.30.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.31.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.31.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.31.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.4.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.4.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.4.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.5.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.5.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.5.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.6.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.6.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.6.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.7.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.7.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.7.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.8.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.8.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.8.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.9.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.9.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.experts.9.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.ffn_layer.gate.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.norm1.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.norm2.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.self_attn.gate_proj.bias": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.self_attn.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.self_attn.k_scale": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.self_attn.q_scale": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.layer.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.norm.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.norm_embeds.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.norm_hidden.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.8.projection_matrix.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.0.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.0.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.0.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.1.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.1.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.1.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.10.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.10.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.10.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.11.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.11.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.11.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.12.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.12.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.12.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.13.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.13.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.13.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.14.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.14.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.14.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.15.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.15.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.15.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.16.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.16.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.16.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.17.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.17.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.17.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.18.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.18.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.18.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.19.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.19.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.19.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.2.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.2.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.2.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.20.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.20.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.20.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.21.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.21.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.21.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.22.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.22.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.22.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.23.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.23.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.23.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.24.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.24.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.24.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.25.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.25.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.25.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.26.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.26.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.26.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.27.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.27.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.27.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.28.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.28.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.28.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.29.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.29.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.29.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.3.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.3.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.3.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.30.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.30.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.30.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.31.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.31.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.31.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.4.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.4.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.4.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.5.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.5.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.5.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.6.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.6.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.6.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.7.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.7.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.7.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.8.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.8.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.8.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.9.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.9.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.experts.9.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.ffn_layer.gate.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.norm1.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.norm2.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.self_attn.gate_proj.bias": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.self_attn.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.self_attn.k_scale": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.self_attn.q_scale": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.layer.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.norm.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.norm_embeds.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.norm_hidden.weight": "model-00003-of-00004.safetensors", | |
| "mtp_modules.9.projection_matrix.weight": "model-00003-of-00004.safetensors", | |
| "output_patch_embedding.hidden_layer.bias": "model-00002-of-00004.safetensors", | |
| "output_patch_embedding.hidden_layer.weight": "model-00002-of-00004.safetensors", | |
| "output_patch_embedding.output_layer.bias": "model-00002-of-00004.safetensors", | |
| "output_patch_embedding.output_layer.weight": "model-00002-of-00004.safetensors", | |
| "output_patch_embedding.residual_layer.bias": "model-00002-of-00004.safetensors", | |
| "output_patch_embedding.residual_layer.weight": "model-00002-of-00004.safetensors" | |
| } | |
| } | |