| { |
| "architectures": [ |
| "InternVLForConditionalGeneration" |
| ], |
| "downsample_ratio": 0.5, |
| "image_seq_length": 256, |
| "image_token_index": 151667, |
| "model_type": "internvl", |
| "projector_hidden_act": "gelu", |
| "text_config": { |
| "architectures": [ |
| "Qwen2ForCausalLM" |
| ], |
| "attention_dropout": 0.0, |
| "bos_token_id": 151643, |
| "eos_token_id": 151645, |
| "hidden_act": "silu", |
| "hidden_size": 5120, |
| "initializer_range": 0.02, |
| "intermediate_size": 27648, |
| "max_position_embeddings": 32768, |
| "max_window_layers": 70, |
| "model_type": "qwen2", |
| "num_attention_heads": 40, |
| "num_hidden_layers": 64, |
| "num_key_value_heads": 8, |
| "rms_norm_eps": 1e-06, |
| "rope_scaling": { |
| "factor": 2.0, |
| "rope_type": "dynamic", |
| "type": "dynamic" |
| }, |
| "rope_theta": 1000000.0, |
| "sliding_window": null, |
| "torch_dtype": "bfloat16", |
| "use_cache": true, |
| "use_sliding_window": false, |
| "vocab_size": 151674 |
| }, |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.52.0.dev0", |
| "vision_config": { |
| "architectures": [ |
| "InternVisionModel" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "dropout": 0.0, |
| "hidden_act": "gelu", |
| "hidden_dropout_prob": 0.0, |
| "hidden_size": 3200, |
| "image_size": [ |
| 448, |
| 448 |
| ], |
| "initializer_factor": 0.1, |
| "initializer_range": 1e-10, |
| "intermediate_size": 12800, |
| "layer_norm_eps": 1e-06, |
| "layer_scale_init_value": 0.1, |
| "model_type": "internvl_vision", |
| "norm_type": "rms_norm", |
| "num_attention_heads": 25, |
| "num_channels": 3, |
| "num_hidden_layers": 45, |
| "patch_size": [ |
| 14, |
| 14 |
| ], |
| "projection_dropout": 0.0, |
| "torch_dtype": "bfloat16", |
| "use_absolute_position_embeddings": true, |
| "use_mask_token": false, |
| "use_mean_pooling": true, |
| "use_qk_norm": true |
| }, |
| "vision_feature_layer": -1, |
| "vision_feature_select_strategy": "default" |
| } |
|
|
