Instructions to use iyaja/alpacapp-30B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use iyaja/alpacapp-30B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="iyaja/alpacapp-30B")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("iyaja/alpacapp-30B") model = AutoModelForCausalLM.from_pretrained("iyaja/alpacapp-30B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use iyaja/alpacapp-30B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "iyaja/alpacapp-30B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "iyaja/alpacapp-30B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/iyaja/alpacapp-30B
- SGLang
How to use iyaja/alpacapp-30B with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "iyaja/alpacapp-30B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "iyaja/alpacapp-30B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "iyaja/alpacapp-30B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "iyaja/alpacapp-30B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use iyaja/alpacapp-30B with Docker Model Runner:
docker model run hf.co/iyaja/alpacapp-30B
Upload LlamaForCausalLM
Browse files- config.json +23 -0
- generation_config.json +7 -0
- pytorch_model-00001-of-00034.bin +3 -0
- pytorch_model-00002-of-00034.bin +3 -0
- pytorch_model-00003-of-00034.bin +3 -0
- pytorch_model-00004-of-00034.bin +3 -0
- pytorch_model-00005-of-00034.bin +3 -0
- pytorch_model-00006-of-00034.bin +3 -0
- pytorch_model-00007-of-00034.bin +3 -0
- pytorch_model-00008-of-00034.bin +3 -0
- pytorch_model-00009-of-00034.bin +3 -0
- pytorch_model-00010-of-00034.bin +3 -0
- pytorch_model-00011-of-00034.bin +3 -0
- pytorch_model-00012-of-00034.bin +3 -0
- pytorch_model-00013-of-00034.bin +3 -0
- pytorch_model-00014-of-00034.bin +3 -0
- pytorch_model-00015-of-00034.bin +3 -0
- pytorch_model-00016-of-00034.bin +3 -0
- pytorch_model-00017-of-00034.bin +3 -0
- pytorch_model-00018-of-00034.bin +3 -0
- pytorch_model-00019-of-00034.bin +3 -0
- pytorch_model-00020-of-00034.bin +3 -0
- pytorch_model-00021-of-00034.bin +3 -0
- pytorch_model-00022-of-00034.bin +3 -0
- pytorch_model-00023-of-00034.bin +3 -0
- pytorch_model-00024-of-00034.bin +3 -0
- pytorch_model-00025-of-00034.bin +3 -0
- pytorch_model-00026-of-00034.bin +3 -0
- pytorch_model-00027-of-00034.bin +3 -0
- pytorch_model-00028-of-00034.bin +3 -0
- pytorch_model-00029-of-00034.bin +3 -0
- pytorch_model-00030-of-00034.bin +3 -0
- pytorch_model-00031-of-00034.bin +3 -0
- pytorch_model-00032-of-00034.bin +3 -0
- pytorch_model-00033-of-00034.bin +3 -0
- pytorch_model-00034-of-00034.bin +3 -0
- pytorch_model.bin.index.json +610 -0
config.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "decapoda-research/llama-30b-hf",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"bos_token_id": 0,
|
| 7 |
+
"eos_token_id": 1,
|
| 8 |
+
"hidden_act": "silu",
|
| 9 |
+
"hidden_size": 6656,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 17920,
|
| 12 |
+
"max_sequence_length": 2048,
|
| 13 |
+
"model_type": "llama",
|
| 14 |
+
"num_attention_heads": 52,
|
| 15 |
+
"num_hidden_layers": 60,
|
| 16 |
+
"pad_token_id": -1,
|
| 17 |
+
"rms_norm_eps": 1e-06,
|
| 18 |
+
"tie_word_embeddings": false,
|
| 19 |
+
"torch_dtype": "float16",
|
| 20 |
+
"transformers_version": "4.28.0.dev0",
|
| 21 |
+
"use_cache": true,
|
| 22 |
+
"vocab_size": 32000
|
| 23 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"eos_token_id": 1,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.28.0.dev0"
|
| 7 |
+
}
|
pytorch_model-00001-of-00034.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:54085992a9e033a6576f751247ce129d2cdd15eecad958d3193495ab5f94eb91
|
| 3 |
+
size 2118024989
|
pytorch_model-00002-of-00034.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:50d5661a5edd66f8a48fa14d6fd10367c1d6a56c25f52f937085c90a082c2c19
|
| 3 |
+
size 2498029213
|
pytorch_model-00003-of-00034.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:60915c1caaaac376e8ed71fb878b3b9b82515e6b42a499995d34a12712fcc36a
|
| 3 |
+
size 2498029743
|
pytorch_model-00004-of-00034.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:79b756c6f48f7a9e741c3f87499e032eb429e2ecad0da69c744788bc17f1b44c
|
| 3 |
+
size 2169143407
|
pytorch_model-00005-of-00034.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1a2eabe88034fbd2b753b835a8d5819f21de42db8dcbe79864043775e6658706
|
| 3 |
+
size 2436688385
|
pytorch_model-00006-of-00034.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:28d21d5f40e63669a5276ae33dbe4839fbd6df71b88850c54210e9beb2b4f8ad
|
| 3 |
+
size 2436688385
|
pytorch_model-00007-of-00034.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:72552839994c28d44f0b53c321f6929634a86b765339f12b7735b7bae5f87c3b
|
| 3 |
+
size 2498029213
|
pytorch_model-00008-of-00034.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0600957bafbaed993b18a822957f7cfa591cc9f2d118541fbc489d36c704326b
|
| 3 |
+
size 2498029807
|
pytorch_model-00009-of-00034.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d571bf7d6a96380581286a847c0a78e52f807bff5565f5c89c75777f8c64b0c4
|
| 3 |
+
size 2169143407
|
pytorch_model-00010-of-00034.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e56dd9aecabcbecee17ae4d9ea5ee5b5e8a1386a66d13a521f65d79b293eec16
|
| 3 |
+
size 2436688385
|
pytorch_model-00011-of-00034.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9352a3f6dee57537ab2c9115d3bd597ad4de9d9427a0e75ad52ec083b4ed191c
|
| 3 |
+
size 2436688385
|
pytorch_model-00012-of-00034.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:94d0f58673047f9644583688d53032889f0d3cd033e45aef92ee9937c6ec0846
|
| 3 |
+
size 2498029213
|
pytorch_model-00013-of-00034.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:31c1265f4dc83d57fdceb3c392e3b9e26c9ebec6537cca06a608afa6d593d2a4
|
| 3 |
+
size 2498029807
|
pytorch_model-00014-of-00034.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6790ec0c2b3211243804cabe50bbc3bdadc453c716a340d871446e5551cdd502
|
| 3 |
+
size 2169143407
|
pytorch_model-00015-of-00034.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f820fe01678bb0675cd267895d8564aba1e8e0772852612f6777b2997001faa6
|
| 3 |
+
size 2436688385
|
pytorch_model-00016-of-00034.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7519e5ef3dfb6fcc37f702b099b4c4d2f42fdc3debe17ac0f332f8cf3e5aac39
|
| 3 |
+
size 2436688385
|
pytorch_model-00017-of-00034.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cf0f9617fb713a48074c1cc4ecd88435837f596bdc106a11f0e85fcb4c87bace
|
| 3 |
+
size 2498029213
|
pytorch_model-00018-of-00034.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bfc40f95e82b734973f57038ce0510a372c5c8bc18cf84ac36ee756aae74d468
|
| 3 |
+
size 2498029807
|
pytorch_model-00019-of-00034.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fe435253b339881e1cbec9caae0a8ecd0737447f783f27b06634679652fa6d1b
|
| 3 |
+
size 2169143407
|
pytorch_model-00020-of-00034.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ad7c1c99236ecb7bdd1f20d1af611464561539b89e22b555fc74100eca80bf8f
|
| 3 |
+
size 2436688385
|
pytorch_model-00021-of-00034.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:49943b06a59ca7130282aad2443f407e794cfdbb6d2772745e8c72665fc5a77e
|
| 3 |
+
size 2436688385
|
pytorch_model-00022-of-00034.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6d53a1819fbb03409c3a24653e838a08ee0d0bc0c65766b128766f4ea43a4452
|
| 3 |
+
size 2498029213
|
pytorch_model-00023-of-00034.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:23edb90b6d111bfcdc43695cc9db56a772b45cfe76920cfb69fbd7b0b64f0527
|
| 3 |
+
size 2498029807
|
pytorch_model-00024-of-00034.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:607ac7066de3a9c9991ca2ee2bd8c861a21664e490588f8fb64180b35c818003
|
| 3 |
+
size 2169143407
|
pytorch_model-00025-of-00034.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4169373484410bffbf797f9236fde9c501ee99e064ad789d9aa21b57d4aac800
|
| 3 |
+
size 2436688385
|
pytorch_model-00026-of-00034.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f597d6e575cd904f3b263f8846a581146e782eedaa4b8b5f4181005d774c1e1a
|
| 3 |
+
size 2436688385
|
pytorch_model-00027-of-00034.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0ddb7593cdaa8154e49c8f0a91ca8bc26f29d85428d9bc02469023b7ae6d6ef4
|
| 3 |
+
size 2498029213
|
pytorch_model-00028-of-00034.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:64e650a84c46c315a796519c8321f7c9fca1754399176a91d87b52f7356731ca
|
| 3 |
+
size 2498029807
|
pytorch_model-00029-of-00034.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3d4ba5e0a1934407e9897b797ab74368c7435628ee1f8fefa0d90b047100046c
|
| 3 |
+
size 2169143407
|
pytorch_model-00030-of-00034.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:09c2949c286d80ce45cf741c29bf38081dff8d4e4debe1d4bbbfacdf18087d37
|
| 3 |
+
size 2436688385
|
pytorch_model-00031-of-00034.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ea62c61d0bbd14a294ab500fda9ffed8e61cc1be524f1d9e342cc8a5e8b8e8d5
|
| 3 |
+
size 2436688385
|
pytorch_model-00032-of-00034.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b1b0d27ddaf8cdf557e4528c308dd201f9350aa1e76a6fb656a09a908a37642d
|
| 3 |
+
size 2498029213
|
pytorch_model-00033-of-00034.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:199809e33323186d3d12ded2a1ef31cb6dc2f84002424eccb68c84c9db9e80ff
|
| 3 |
+
size 2498029807
|
pytorch_model-00034-of-00034.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:80e5585e202629bbb07490524ecddbbf2eb926eba4c698028332497de7b7504a
|
| 3 |
+
size 1976610069
|
pytorch_model.bin.index.json
ADDED
|
@@ -0,0 +1,610 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 65057902592
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.weight": "pytorch_model-00034-of-00034.bin",
|
| 7 |
+
"model.embed_tokens.weight": "pytorch_model-00001-of-00034.bin",
|
| 8 |
+
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00034.bin",
|
| 9 |
+
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00034.bin",
|
| 10 |
+
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00034.bin",
|
| 11 |
+
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00034.bin",
|
| 12 |
+
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00034.bin",
|
| 13 |
+
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00034.bin",
|
| 14 |
+
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00034.bin",
|
| 15 |
+
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00034.bin",
|
| 16 |
+
"model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00034.bin",
|
| 17 |
+
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00034.bin",
|
| 18 |
+
"model.layers.1.input_layernorm.weight": "pytorch_model-00002-of-00034.bin",
|
| 19 |
+
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00002-of-00034.bin",
|
| 20 |
+
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00002-of-00034.bin",
|
| 21 |
+
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00002-of-00034.bin",
|
| 22 |
+
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00002-of-00034.bin",
|
| 23 |
+
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00034.bin",
|
| 24 |
+
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00034.bin",
|
| 25 |
+
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00034.bin",
|
| 26 |
+
"model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00034.bin",
|
| 27 |
+
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00034.bin",
|
| 28 |
+
"model.layers.10.input_layernorm.weight": "pytorch_model-00007-of-00034.bin",
|
| 29 |
+
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00007-of-00034.bin",
|
| 30 |
+
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00007-of-00034.bin",
|
| 31 |
+
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00007-of-00034.bin",
|
| 32 |
+
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00007-of-00034.bin",
|
| 33 |
+
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00006-of-00034.bin",
|
| 34 |
+
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00006-of-00034.bin",
|
| 35 |
+
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00006-of-00034.bin",
|
| 36 |
+
"model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00034.bin",
|
| 37 |
+
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00006-of-00034.bin",
|
| 38 |
+
"model.layers.11.input_layernorm.weight": "pytorch_model-00007-of-00034.bin",
|
| 39 |
+
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00007-of-00034.bin",
|
| 40 |
+
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00007-of-00034.bin",
|
| 41 |
+
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00007-of-00034.bin",
|
| 42 |
+
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00007-of-00034.bin",
|
| 43 |
+
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00007-of-00034.bin",
|
| 44 |
+
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00007-of-00034.bin",
|
| 45 |
+
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00007-of-00034.bin",
|
| 46 |
+
"model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00034.bin",
|
| 47 |
+
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00007-of-00034.bin",
|
| 48 |
+
"model.layers.12.input_layernorm.weight": "pytorch_model-00008-of-00034.bin",
|
| 49 |
+
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00008-of-00034.bin",
|
| 50 |
+
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00008-of-00034.bin",
|
| 51 |
+
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00008-of-00034.bin",
|
| 52 |
+
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00008-of-00034.bin",
|
| 53 |
+
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00007-of-00034.bin",
|
| 54 |
+
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00008-of-00034.bin",
|
| 55 |
+
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00007-of-00034.bin",
|
| 56 |
+
"model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00034.bin",
|
| 57 |
+
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00008-of-00034.bin",
|
| 58 |
+
"model.layers.13.input_layernorm.weight": "pytorch_model-00008-of-00034.bin",
|
| 59 |
+
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00008-of-00034.bin",
|
| 60 |
+
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00008-of-00034.bin",
|
| 61 |
+
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00008-of-00034.bin",
|
| 62 |
+
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00008-of-00034.bin",
|
| 63 |
+
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00008-of-00034.bin",
|
| 64 |
+
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00008-of-00034.bin",
|
| 65 |
+
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00008-of-00034.bin",
|
| 66 |
+
"model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00034.bin",
|
| 67 |
+
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00008-of-00034.bin",
|
| 68 |
+
"model.layers.14.input_layernorm.weight": "pytorch_model-00009-of-00034.bin",
|
| 69 |
+
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00009-of-00034.bin",
|
| 70 |
+
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00009-of-00034.bin",
|
| 71 |
+
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00009-of-00034.bin",
|
| 72 |
+
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00009-of-00034.bin",
|
| 73 |
+
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00009-of-00034.bin",
|
| 74 |
+
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00009-of-00034.bin",
|
| 75 |
+
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00009-of-00034.bin",
|
| 76 |
+
"model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00034.bin",
|
| 77 |
+
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00009-of-00034.bin",
|
| 78 |
+
"model.layers.15.input_layernorm.weight": "pytorch_model-00010-of-00034.bin",
|
| 79 |
+
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00009-of-00034.bin",
|
| 80 |
+
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00009-of-00034.bin",
|
| 81 |
+
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00010-of-00034.bin",
|
| 82 |
+
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00010-of-00034.bin",
|
| 83 |
+
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00009-of-00034.bin",
|
| 84 |
+
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00009-of-00034.bin",
|
| 85 |
+
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00009-of-00034.bin",
|
| 86 |
+
"model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00034.bin",
|
| 87 |
+
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00009-of-00034.bin",
|
| 88 |
+
"model.layers.16.input_layernorm.weight": "pytorch_model-00010-of-00034.bin",
|
| 89 |
+
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00010-of-00034.bin",
|
| 90 |
+
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00010-of-00034.bin",
|
| 91 |
+
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00010-of-00034.bin",
|
| 92 |
+
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00010-of-00034.bin",
|
| 93 |
+
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00010-of-00034.bin",
|
| 94 |
+
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00010-of-00034.bin",
|
| 95 |
+
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00010-of-00034.bin",
|
| 96 |
+
"model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00034.bin",
|
| 97 |
+
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00010-of-00034.bin",
|
| 98 |
+
"model.layers.17.input_layernorm.weight": "pytorch_model-00011-of-00034.bin",
|
| 99 |
+
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00011-of-00034.bin",
|
| 100 |
+
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00010-of-00034.bin",
|
| 101 |
+
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00011-of-00034.bin",
|
| 102 |
+
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00011-of-00034.bin",
|
| 103 |
+
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00010-of-00034.bin",
|
| 104 |
+
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00010-of-00034.bin",
|
| 105 |
+
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00010-of-00034.bin",
|
| 106 |
+
"model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00034.bin",
|
| 107 |
+
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00010-of-00034.bin",
|
| 108 |
+
"model.layers.18.input_layernorm.weight": "pytorch_model-00011-of-00034.bin",
|
| 109 |
+
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00011-of-00034.bin",
|
| 110 |
+
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00011-of-00034.bin",
|
| 111 |
+
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00011-of-00034.bin",
|
| 112 |
+
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00011-of-00034.bin",
|
| 113 |
+
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00011-of-00034.bin",
|
| 114 |
+
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00011-of-00034.bin",
|
| 115 |
+
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00011-of-00034.bin",
|
| 116 |
+
"model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00034.bin",
|
| 117 |
+
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00011-of-00034.bin",
|
| 118 |
+
"model.layers.19.input_layernorm.weight": "pytorch_model-00012-of-00034.bin",
|
| 119 |
+
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00012-of-00034.bin",
|
| 120 |
+
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00012-of-00034.bin",
|
| 121 |
+
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00012-of-00034.bin",
|
| 122 |
+
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00012-of-00034.bin",
|
| 123 |
+
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00011-of-00034.bin",
|
| 124 |
+
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00011-of-00034.bin",
|
| 125 |
+
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00011-of-00034.bin",
|
| 126 |
+
"model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00034.bin",
|
| 127 |
+
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00011-of-00034.bin",
|
| 128 |
+
"model.layers.2.input_layernorm.weight": "pytorch_model-00002-of-00034.bin",
|
| 129 |
+
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00002-of-00034.bin",
|
| 130 |
+
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00002-of-00034.bin",
|
| 131 |
+
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00002-of-00034.bin",
|
| 132 |
+
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00002-of-00034.bin",
|
| 133 |
+
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00002-of-00034.bin",
|
| 134 |
+
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00002-of-00034.bin",
|
| 135 |
+
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00002-of-00034.bin",
|
| 136 |
+
"model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00034.bin",
|
| 137 |
+
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00002-of-00034.bin",
|
| 138 |
+
"model.layers.20.input_layernorm.weight": "pytorch_model-00012-of-00034.bin",
|
| 139 |
+
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00012-of-00034.bin",
|
| 140 |
+
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00012-of-00034.bin",
|
| 141 |
+
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00012-of-00034.bin",
|
| 142 |
+
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00012-of-00034.bin",
|
| 143 |
+
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00012-of-00034.bin",
|
| 144 |
+
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00012-of-00034.bin",
|
| 145 |
+
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00012-of-00034.bin",
|
| 146 |
+
"model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00034.bin",
|
| 147 |
+
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00012-of-00034.bin",
|
| 148 |
+
"model.layers.21.input_layernorm.weight": "pytorch_model-00013-of-00034.bin",
|
| 149 |
+
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00013-of-00034.bin",
|
| 150 |
+
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00013-of-00034.bin",
|
| 151 |
+
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00013-of-00034.bin",
|
| 152 |
+
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00013-of-00034.bin",
|
| 153 |
+
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00012-of-00034.bin",
|
| 154 |
+
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00013-of-00034.bin",
|
| 155 |
+
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00012-of-00034.bin",
|
| 156 |
+
"model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00034.bin",
|
| 157 |
+
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00013-of-00034.bin",
|
| 158 |
+
"model.layers.22.input_layernorm.weight": "pytorch_model-00013-of-00034.bin",
|
| 159 |
+
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00013-of-00034.bin",
|
| 160 |
+
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00013-of-00034.bin",
|
| 161 |
+
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00013-of-00034.bin",
|
| 162 |
+
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00013-of-00034.bin",
|
| 163 |
+
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00013-of-00034.bin",
|
| 164 |
+
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00013-of-00034.bin",
|
| 165 |
+
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00013-of-00034.bin",
|
| 166 |
+
"model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00034.bin",
|
| 167 |
+
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00013-of-00034.bin",
|
| 168 |
+
"model.layers.23.input_layernorm.weight": "pytorch_model-00014-of-00034.bin",
|
| 169 |
+
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00014-of-00034.bin",
|
| 170 |
+
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00014-of-00034.bin",
|
| 171 |
+
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00014-of-00034.bin",
|
| 172 |
+
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00014-of-00034.bin",
|
| 173 |
+
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00014-of-00034.bin",
|
| 174 |
+
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00014-of-00034.bin",
|
| 175 |
+
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00014-of-00034.bin",
|
| 176 |
+
"model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00014-of-00034.bin",
|
| 177 |
+
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00014-of-00034.bin",
|
| 178 |
+
"model.layers.24.input_layernorm.weight": "pytorch_model-00015-of-00034.bin",
|
| 179 |
+
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00014-of-00034.bin",
|
| 180 |
+
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00014-of-00034.bin",
|
| 181 |
+
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00015-of-00034.bin",
|
| 182 |
+
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00015-of-00034.bin",
|
| 183 |
+
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00014-of-00034.bin",
|
| 184 |
+
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00014-of-00034.bin",
|
| 185 |
+
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00014-of-00034.bin",
|
| 186 |
+
"model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00014-of-00034.bin",
|
| 187 |
+
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00014-of-00034.bin",
|
| 188 |
+
"model.layers.25.input_layernorm.weight": "pytorch_model-00015-of-00034.bin",
|
| 189 |
+
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00015-of-00034.bin",
|
| 190 |
+
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00015-of-00034.bin",
|
| 191 |
+
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00015-of-00034.bin",
|
| 192 |
+
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00015-of-00034.bin",
|
| 193 |
+
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00015-of-00034.bin",
|
| 194 |
+
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00015-of-00034.bin",
|
| 195 |
+
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00015-of-00034.bin",
|
| 196 |
+
"model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00015-of-00034.bin",
|
| 197 |
+
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00015-of-00034.bin",
|
| 198 |
+
"model.layers.26.input_layernorm.weight": "pytorch_model-00016-of-00034.bin",
|
| 199 |
+
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00016-of-00034.bin",
|
| 200 |
+
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00015-of-00034.bin",
|
| 201 |
+
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00016-of-00034.bin",
|
| 202 |
+
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00016-of-00034.bin",
|
| 203 |
+
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00015-of-00034.bin",
|
| 204 |
+
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00015-of-00034.bin",
|
| 205 |
+
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00015-of-00034.bin",
|
| 206 |
+
"model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00015-of-00034.bin",
|
| 207 |
+
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00015-of-00034.bin",
|
| 208 |
+
"model.layers.27.input_layernorm.weight": "pytorch_model-00016-of-00034.bin",
|
| 209 |
+
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00016-of-00034.bin",
|
| 210 |
+
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00016-of-00034.bin",
|
| 211 |
+
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00016-of-00034.bin",
|
| 212 |
+
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00016-of-00034.bin",
|
| 213 |
+
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00016-of-00034.bin",
|
| 214 |
+
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00016-of-00034.bin",
|
| 215 |
+
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00016-of-00034.bin",
|
| 216 |
+
"model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00016-of-00034.bin",
|
| 217 |
+
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00016-of-00034.bin",
|
| 218 |
+
"model.layers.28.input_layernorm.weight": "pytorch_model-00017-of-00034.bin",
|
| 219 |
+
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00017-of-00034.bin",
|
| 220 |
+
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00017-of-00034.bin",
|
| 221 |
+
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00017-of-00034.bin",
|
| 222 |
+
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00017-of-00034.bin",
|
| 223 |
+
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00016-of-00034.bin",
|
| 224 |
+
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00016-of-00034.bin",
|
| 225 |
+
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00016-of-00034.bin",
|
| 226 |
+
"model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00016-of-00034.bin",
|
| 227 |
+
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00016-of-00034.bin",
|
| 228 |
+
"model.layers.29.input_layernorm.weight": "pytorch_model-00017-of-00034.bin",
|
| 229 |
+
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00017-of-00034.bin",
|
| 230 |
+
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00017-of-00034.bin",
|
| 231 |
+
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00017-of-00034.bin",
|
| 232 |
+
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00017-of-00034.bin",
|
| 233 |
+
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00017-of-00034.bin",
|
| 234 |
+
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00017-of-00034.bin",
|
| 235 |
+
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00017-of-00034.bin",
|
| 236 |
+
"model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00017-of-00034.bin",
|
| 237 |
+
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00017-of-00034.bin",
|
| 238 |
+
"model.layers.3.input_layernorm.weight": "pytorch_model-00003-of-00034.bin",
|
| 239 |
+
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00003-of-00034.bin",
|
| 240 |
+
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00003-of-00034.bin",
|
| 241 |
+
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00003-of-00034.bin",
|
| 242 |
+
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00003-of-00034.bin",
|
| 243 |
+
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00002-of-00034.bin",
|
| 244 |
+
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00003-of-00034.bin",
|
| 245 |
+
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00002-of-00034.bin",
|
| 246 |
+
"model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00034.bin",
|
| 247 |
+
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00003-of-00034.bin",
|
| 248 |
+
"model.layers.30.input_layernorm.weight": "pytorch_model-00018-of-00034.bin",
|
| 249 |
+
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00018-of-00034.bin",
|
| 250 |
+
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00018-of-00034.bin",
|
| 251 |
+
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00018-of-00034.bin",
|
| 252 |
+
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00018-of-00034.bin",
|
| 253 |
+
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00017-of-00034.bin",
|
| 254 |
+
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00018-of-00034.bin",
|
| 255 |
+
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00017-of-00034.bin",
|
| 256 |
+
"model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00018-of-00034.bin",
|
| 257 |
+
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00018-of-00034.bin",
|
| 258 |
+
"model.layers.31.input_layernorm.weight": "pytorch_model-00018-of-00034.bin",
|
| 259 |
+
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00018-of-00034.bin",
|
| 260 |
+
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00018-of-00034.bin",
|
| 261 |
+
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00018-of-00034.bin",
|
| 262 |
+
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00018-of-00034.bin",
|
| 263 |
+
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00018-of-00034.bin",
|
| 264 |
+
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00018-of-00034.bin",
|
| 265 |
+
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00018-of-00034.bin",
|
| 266 |
+
"model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00018-of-00034.bin",
|
| 267 |
+
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00018-of-00034.bin",
|
| 268 |
+
"model.layers.32.input_layernorm.weight": "pytorch_model-00019-of-00034.bin",
|
| 269 |
+
"model.layers.32.mlp.down_proj.weight": "pytorch_model-00019-of-00034.bin",
|
| 270 |
+
"model.layers.32.mlp.gate_proj.weight": "pytorch_model-00019-of-00034.bin",
|
| 271 |
+
"model.layers.32.mlp.up_proj.weight": "pytorch_model-00019-of-00034.bin",
|
| 272 |
+
"model.layers.32.post_attention_layernorm.weight": "pytorch_model-00019-of-00034.bin",
|
| 273 |
+
"model.layers.32.self_attn.k_proj.weight": "pytorch_model-00019-of-00034.bin",
|
| 274 |
+
"model.layers.32.self_attn.o_proj.weight": "pytorch_model-00019-of-00034.bin",
|
| 275 |
+
"model.layers.32.self_attn.q_proj.weight": "pytorch_model-00019-of-00034.bin",
|
| 276 |
+
"model.layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-00019-of-00034.bin",
|
| 277 |
+
"model.layers.32.self_attn.v_proj.weight": "pytorch_model-00019-of-00034.bin",
|
| 278 |
+
"model.layers.33.input_layernorm.weight": "pytorch_model-00020-of-00034.bin",
|
| 279 |
+
"model.layers.33.mlp.down_proj.weight": "pytorch_model-00019-of-00034.bin",
|
| 280 |
+
"model.layers.33.mlp.gate_proj.weight": "pytorch_model-00019-of-00034.bin",
|
| 281 |
+
"model.layers.33.mlp.up_proj.weight": "pytorch_model-00020-of-00034.bin",
|
| 282 |
+
"model.layers.33.post_attention_layernorm.weight": "pytorch_model-00020-of-00034.bin",
|
| 283 |
+
"model.layers.33.self_attn.k_proj.weight": "pytorch_model-00019-of-00034.bin",
|
| 284 |
+
"model.layers.33.self_attn.o_proj.weight": "pytorch_model-00019-of-00034.bin",
|
| 285 |
+
"model.layers.33.self_attn.q_proj.weight": "pytorch_model-00019-of-00034.bin",
|
| 286 |
+
"model.layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-00019-of-00034.bin",
|
| 287 |
+
"model.layers.33.self_attn.v_proj.weight": "pytorch_model-00019-of-00034.bin",
|
| 288 |
+
"model.layers.34.input_layernorm.weight": "pytorch_model-00020-of-00034.bin",
|
| 289 |
+
"model.layers.34.mlp.down_proj.weight": "pytorch_model-00020-of-00034.bin",
|
| 290 |
+
"model.layers.34.mlp.gate_proj.weight": "pytorch_model-00020-of-00034.bin",
|
| 291 |
+
"model.layers.34.mlp.up_proj.weight": "pytorch_model-00020-of-00034.bin",
|
| 292 |
+
"model.layers.34.post_attention_layernorm.weight": "pytorch_model-00020-of-00034.bin",
|
| 293 |
+
"model.layers.34.self_attn.k_proj.weight": "pytorch_model-00020-of-00034.bin",
|
| 294 |
+
"model.layers.34.self_attn.o_proj.weight": "pytorch_model-00020-of-00034.bin",
|
| 295 |
+
"model.layers.34.self_attn.q_proj.weight": "pytorch_model-00020-of-00034.bin",
|
| 296 |
+
"model.layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-00020-of-00034.bin",
|
| 297 |
+
"model.layers.34.self_attn.v_proj.weight": "pytorch_model-00020-of-00034.bin",
|
| 298 |
+
"model.layers.35.input_layernorm.weight": "pytorch_model-00021-of-00034.bin",
|
| 299 |
+
"model.layers.35.mlp.down_proj.weight": "pytorch_model-00021-of-00034.bin",
|
| 300 |
+
"model.layers.35.mlp.gate_proj.weight": "pytorch_model-00020-of-00034.bin",
|
| 301 |
+
"model.layers.35.mlp.up_proj.weight": "pytorch_model-00021-of-00034.bin",
|
| 302 |
+
"model.layers.35.post_attention_layernorm.weight": "pytorch_model-00021-of-00034.bin",
|
| 303 |
+
"model.layers.35.self_attn.k_proj.weight": "pytorch_model-00020-of-00034.bin",
|
| 304 |
+
"model.layers.35.self_attn.o_proj.weight": "pytorch_model-00020-of-00034.bin",
|
| 305 |
+
"model.layers.35.self_attn.q_proj.weight": "pytorch_model-00020-of-00034.bin",
|
| 306 |
+
"model.layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-00020-of-00034.bin",
|
| 307 |
+
"model.layers.35.self_attn.v_proj.weight": "pytorch_model-00020-of-00034.bin",
|
| 308 |
+
"model.layers.36.input_layernorm.weight": "pytorch_model-00021-of-00034.bin",
|
| 309 |
+
"model.layers.36.mlp.down_proj.weight": "pytorch_model-00021-of-00034.bin",
|
| 310 |
+
"model.layers.36.mlp.gate_proj.weight": "pytorch_model-00021-of-00034.bin",
|
| 311 |
+
"model.layers.36.mlp.up_proj.weight": "pytorch_model-00021-of-00034.bin",
|
| 312 |
+
"model.layers.36.post_attention_layernorm.weight": "pytorch_model-00021-of-00034.bin",
|
| 313 |
+
"model.layers.36.self_attn.k_proj.weight": "pytorch_model-00021-of-00034.bin",
|
| 314 |
+
"model.layers.36.self_attn.o_proj.weight": "pytorch_model-00021-of-00034.bin",
|
| 315 |
+
"model.layers.36.self_attn.q_proj.weight": "pytorch_model-00021-of-00034.bin",
|
| 316 |
+
"model.layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-00021-of-00034.bin",
|
| 317 |
+
"model.layers.36.self_attn.v_proj.weight": "pytorch_model-00021-of-00034.bin",
|
| 318 |
+
"model.layers.37.input_layernorm.weight": "pytorch_model-00022-of-00034.bin",
|
| 319 |
+
"model.layers.37.mlp.down_proj.weight": "pytorch_model-00022-of-00034.bin",
|
| 320 |
+
"model.layers.37.mlp.gate_proj.weight": "pytorch_model-00022-of-00034.bin",
|
| 321 |
+
"model.layers.37.mlp.up_proj.weight": "pytorch_model-00022-of-00034.bin",
|
| 322 |
+
"model.layers.37.post_attention_layernorm.weight": "pytorch_model-00022-of-00034.bin",
|
| 323 |
+
"model.layers.37.self_attn.k_proj.weight": "pytorch_model-00021-of-00034.bin",
|
| 324 |
+
"model.layers.37.self_attn.o_proj.weight": "pytorch_model-00021-of-00034.bin",
|
| 325 |
+
"model.layers.37.self_attn.q_proj.weight": "pytorch_model-00021-of-00034.bin",
|
| 326 |
+
"model.layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-00021-of-00034.bin",
|
| 327 |
+
"model.layers.37.self_attn.v_proj.weight": "pytorch_model-00021-of-00034.bin",
|
| 328 |
+
"model.layers.38.input_layernorm.weight": "pytorch_model-00022-of-00034.bin",
|
| 329 |
+
"model.layers.38.mlp.down_proj.weight": "pytorch_model-00022-of-00034.bin",
|
| 330 |
+
"model.layers.38.mlp.gate_proj.weight": "pytorch_model-00022-of-00034.bin",
|
| 331 |
+
"model.layers.38.mlp.up_proj.weight": "pytorch_model-00022-of-00034.bin",
|
| 332 |
+
"model.layers.38.post_attention_layernorm.weight": "pytorch_model-00022-of-00034.bin",
|
| 333 |
+
"model.layers.38.self_attn.k_proj.weight": "pytorch_model-00022-of-00034.bin",
|
| 334 |
+
"model.layers.38.self_attn.o_proj.weight": "pytorch_model-00022-of-00034.bin",
|
| 335 |
+
"model.layers.38.self_attn.q_proj.weight": "pytorch_model-00022-of-00034.bin",
|
| 336 |
+
"model.layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-00022-of-00034.bin",
|
| 337 |
+
"model.layers.38.self_attn.v_proj.weight": "pytorch_model-00022-of-00034.bin",
|
| 338 |
+
"model.layers.39.input_layernorm.weight": "pytorch_model-00023-of-00034.bin",
|
| 339 |
+
"model.layers.39.mlp.down_proj.weight": "pytorch_model-00023-of-00034.bin",
|
| 340 |
+
"model.layers.39.mlp.gate_proj.weight": "pytorch_model-00023-of-00034.bin",
|
| 341 |
+
"model.layers.39.mlp.up_proj.weight": "pytorch_model-00023-of-00034.bin",
|
| 342 |
+
"model.layers.39.post_attention_layernorm.weight": "pytorch_model-00023-of-00034.bin",
|
| 343 |
+
"model.layers.39.self_attn.k_proj.weight": "pytorch_model-00022-of-00034.bin",
|
| 344 |
+
"model.layers.39.self_attn.o_proj.weight": "pytorch_model-00023-of-00034.bin",
|
| 345 |
+
"model.layers.39.self_attn.q_proj.weight": "pytorch_model-00022-of-00034.bin",
|
| 346 |
+
"model.layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-00023-of-00034.bin",
|
| 347 |
+
"model.layers.39.self_attn.v_proj.weight": "pytorch_model-00023-of-00034.bin",
|
| 348 |
+
"model.layers.4.input_layernorm.weight": "pytorch_model-00003-of-00034.bin",
|
| 349 |
+
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00003-of-00034.bin",
|
| 350 |
+
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00003-of-00034.bin",
|
| 351 |
+
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00003-of-00034.bin",
|
| 352 |
+
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00003-of-00034.bin",
|
| 353 |
+
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00003-of-00034.bin",
|
| 354 |
+
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00003-of-00034.bin",
|
| 355 |
+
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00003-of-00034.bin",
|
| 356 |
+
"model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00034.bin",
|
| 357 |
+
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00003-of-00034.bin",
|
| 358 |
+
"model.layers.40.input_layernorm.weight": "pytorch_model-00023-of-00034.bin",
|
| 359 |
+
"model.layers.40.mlp.down_proj.weight": "pytorch_model-00023-of-00034.bin",
|
| 360 |
+
"model.layers.40.mlp.gate_proj.weight": "pytorch_model-00023-of-00034.bin",
|
| 361 |
+
"model.layers.40.mlp.up_proj.weight": "pytorch_model-00023-of-00034.bin",
|
| 362 |
+
"model.layers.40.post_attention_layernorm.weight": "pytorch_model-00023-of-00034.bin",
|
| 363 |
+
"model.layers.40.self_attn.k_proj.weight": "pytorch_model-00023-of-00034.bin",
|
| 364 |
+
"model.layers.40.self_attn.o_proj.weight": "pytorch_model-00023-of-00034.bin",
|
| 365 |
+
"model.layers.40.self_attn.q_proj.weight": "pytorch_model-00023-of-00034.bin",
|
| 366 |
+
"model.layers.40.self_attn.rotary_emb.inv_freq": "pytorch_model-00023-of-00034.bin",
|
| 367 |
+
"model.layers.40.self_attn.v_proj.weight": "pytorch_model-00023-of-00034.bin",
|
| 368 |
+
"model.layers.41.input_layernorm.weight": "pytorch_model-00024-of-00034.bin",
|
| 369 |
+
"model.layers.41.mlp.down_proj.weight": "pytorch_model-00024-of-00034.bin",
|
| 370 |
+
"model.layers.41.mlp.gate_proj.weight": "pytorch_model-00024-of-00034.bin",
|
| 371 |
+
"model.layers.41.mlp.up_proj.weight": "pytorch_model-00024-of-00034.bin",
|
| 372 |
+
"model.layers.41.post_attention_layernorm.weight": "pytorch_model-00024-of-00034.bin",
|
| 373 |
+
"model.layers.41.self_attn.k_proj.weight": "pytorch_model-00024-of-00034.bin",
|
| 374 |
+
"model.layers.41.self_attn.o_proj.weight": "pytorch_model-00024-of-00034.bin",
|
| 375 |
+
"model.layers.41.self_attn.q_proj.weight": "pytorch_model-00024-of-00034.bin",
|
| 376 |
+
"model.layers.41.self_attn.rotary_emb.inv_freq": "pytorch_model-00024-of-00034.bin",
|
| 377 |
+
"model.layers.41.self_attn.v_proj.weight": "pytorch_model-00024-of-00034.bin",
|
| 378 |
+
"model.layers.42.input_layernorm.weight": "pytorch_model-00025-of-00034.bin",
|
| 379 |
+
"model.layers.42.mlp.down_proj.weight": "pytorch_model-00024-of-00034.bin",
|
| 380 |
+
"model.layers.42.mlp.gate_proj.weight": "pytorch_model-00024-of-00034.bin",
|
| 381 |
+
"model.layers.42.mlp.up_proj.weight": "pytorch_model-00025-of-00034.bin",
|
| 382 |
+
"model.layers.42.post_attention_layernorm.weight": "pytorch_model-00025-of-00034.bin",
|
| 383 |
+
"model.layers.42.self_attn.k_proj.weight": "pytorch_model-00024-of-00034.bin",
|
| 384 |
+
"model.layers.42.self_attn.o_proj.weight": "pytorch_model-00024-of-00034.bin",
|
| 385 |
+
"model.layers.42.self_attn.q_proj.weight": "pytorch_model-00024-of-00034.bin",
|
| 386 |
+
"model.layers.42.self_attn.rotary_emb.inv_freq": "pytorch_model-00024-of-00034.bin",
|
| 387 |
+
"model.layers.42.self_attn.v_proj.weight": "pytorch_model-00024-of-00034.bin",
|
| 388 |
+
"model.layers.43.input_layernorm.weight": "pytorch_model-00025-of-00034.bin",
|
| 389 |
+
"model.layers.43.mlp.down_proj.weight": "pytorch_model-00025-of-00034.bin",
|
| 390 |
+
"model.layers.43.mlp.gate_proj.weight": "pytorch_model-00025-of-00034.bin",
|
| 391 |
+
"model.layers.43.mlp.up_proj.weight": "pytorch_model-00025-of-00034.bin",
|
| 392 |
+
"model.layers.43.post_attention_layernorm.weight": "pytorch_model-00025-of-00034.bin",
|
| 393 |
+
"model.layers.43.self_attn.k_proj.weight": "pytorch_model-00025-of-00034.bin",
|
| 394 |
+
"model.layers.43.self_attn.o_proj.weight": "pytorch_model-00025-of-00034.bin",
|
| 395 |
+
"model.layers.43.self_attn.q_proj.weight": "pytorch_model-00025-of-00034.bin",
|
| 396 |
+
"model.layers.43.self_attn.rotary_emb.inv_freq": "pytorch_model-00025-of-00034.bin",
|
| 397 |
+
"model.layers.43.self_attn.v_proj.weight": "pytorch_model-00025-of-00034.bin",
|
| 398 |
+
"model.layers.44.input_layernorm.weight": "pytorch_model-00026-of-00034.bin",
|
| 399 |
+
"model.layers.44.mlp.down_proj.weight": "pytorch_model-00026-of-00034.bin",
|
| 400 |
+
"model.layers.44.mlp.gate_proj.weight": "pytorch_model-00025-of-00034.bin",
|
| 401 |
+
"model.layers.44.mlp.up_proj.weight": "pytorch_model-00026-of-00034.bin",
|
| 402 |
+
"model.layers.44.post_attention_layernorm.weight": "pytorch_model-00026-of-00034.bin",
|
| 403 |
+
"model.layers.44.self_attn.k_proj.weight": "pytorch_model-00025-of-00034.bin",
|
| 404 |
+
"model.layers.44.self_attn.o_proj.weight": "pytorch_model-00025-of-00034.bin",
|
| 405 |
+
"model.layers.44.self_attn.q_proj.weight": "pytorch_model-00025-of-00034.bin",
|
| 406 |
+
"model.layers.44.self_attn.rotary_emb.inv_freq": "pytorch_model-00025-of-00034.bin",
|
| 407 |
+
"model.layers.44.self_attn.v_proj.weight": "pytorch_model-00025-of-00034.bin",
|
| 408 |
+
"model.layers.45.input_layernorm.weight": "pytorch_model-00026-of-00034.bin",
|
| 409 |
+
"model.layers.45.mlp.down_proj.weight": "pytorch_model-00026-of-00034.bin",
|
| 410 |
+
"model.layers.45.mlp.gate_proj.weight": "pytorch_model-00026-of-00034.bin",
|
| 411 |
+
"model.layers.45.mlp.up_proj.weight": "pytorch_model-00026-of-00034.bin",
|
| 412 |
+
"model.layers.45.post_attention_layernorm.weight": "pytorch_model-00026-of-00034.bin",
|
| 413 |
+
"model.layers.45.self_attn.k_proj.weight": "pytorch_model-00026-of-00034.bin",
|
| 414 |
+
"model.layers.45.self_attn.o_proj.weight": "pytorch_model-00026-of-00034.bin",
|
| 415 |
+
"model.layers.45.self_attn.q_proj.weight": "pytorch_model-00026-of-00034.bin",
|
| 416 |
+
"model.layers.45.self_attn.rotary_emb.inv_freq": "pytorch_model-00026-of-00034.bin",
|
| 417 |
+
"model.layers.45.self_attn.v_proj.weight": "pytorch_model-00026-of-00034.bin",
|
| 418 |
+
"model.layers.46.input_layernorm.weight": "pytorch_model-00027-of-00034.bin",
|
| 419 |
+
"model.layers.46.mlp.down_proj.weight": "pytorch_model-00027-of-00034.bin",
|
| 420 |
+
"model.layers.46.mlp.gate_proj.weight": "pytorch_model-00027-of-00034.bin",
|
| 421 |
+
"model.layers.46.mlp.up_proj.weight": "pytorch_model-00027-of-00034.bin",
|
| 422 |
+
"model.layers.46.post_attention_layernorm.weight": "pytorch_model-00027-of-00034.bin",
|
| 423 |
+
"model.layers.46.self_attn.k_proj.weight": "pytorch_model-00026-of-00034.bin",
|
| 424 |
+
"model.layers.46.self_attn.o_proj.weight": "pytorch_model-00026-of-00034.bin",
|
| 425 |
+
"model.layers.46.self_attn.q_proj.weight": "pytorch_model-00026-of-00034.bin",
|
| 426 |
+
"model.layers.46.self_attn.rotary_emb.inv_freq": "pytorch_model-00026-of-00034.bin",
|
| 427 |
+
"model.layers.46.self_attn.v_proj.weight": "pytorch_model-00026-of-00034.bin",
|
| 428 |
+
"model.layers.47.input_layernorm.weight": "pytorch_model-00027-of-00034.bin",
|
| 429 |
+
"model.layers.47.mlp.down_proj.weight": "pytorch_model-00027-of-00034.bin",
|
| 430 |
+
"model.layers.47.mlp.gate_proj.weight": "pytorch_model-00027-of-00034.bin",
|
| 431 |
+
"model.layers.47.mlp.up_proj.weight": "pytorch_model-00027-of-00034.bin",
|
| 432 |
+
"model.layers.47.post_attention_layernorm.weight": "pytorch_model-00027-of-00034.bin",
|
| 433 |
+
"model.layers.47.self_attn.k_proj.weight": "pytorch_model-00027-of-00034.bin",
|
| 434 |
+
"model.layers.47.self_attn.o_proj.weight": "pytorch_model-00027-of-00034.bin",
|
| 435 |
+
"model.layers.47.self_attn.q_proj.weight": "pytorch_model-00027-of-00034.bin",
|
| 436 |
+
"model.layers.47.self_attn.rotary_emb.inv_freq": "pytorch_model-00027-of-00034.bin",
|
| 437 |
+
"model.layers.47.self_attn.v_proj.weight": "pytorch_model-00027-of-00034.bin",
|
| 438 |
+
"model.layers.48.input_layernorm.weight": "pytorch_model-00028-of-00034.bin",
|
| 439 |
+
"model.layers.48.mlp.down_proj.weight": "pytorch_model-00028-of-00034.bin",
|
| 440 |
+
"model.layers.48.mlp.gate_proj.weight": "pytorch_model-00028-of-00034.bin",
|
| 441 |
+
"model.layers.48.mlp.up_proj.weight": "pytorch_model-00028-of-00034.bin",
|
| 442 |
+
"model.layers.48.post_attention_layernorm.weight": "pytorch_model-00028-of-00034.bin",
|
| 443 |
+
"model.layers.48.self_attn.k_proj.weight": "pytorch_model-00027-of-00034.bin",
|
| 444 |
+
"model.layers.48.self_attn.o_proj.weight": "pytorch_model-00028-of-00034.bin",
|
| 445 |
+
"model.layers.48.self_attn.q_proj.weight": "pytorch_model-00027-of-00034.bin",
|
| 446 |
+
"model.layers.48.self_attn.rotary_emb.inv_freq": "pytorch_model-00028-of-00034.bin",
|
| 447 |
+
"model.layers.48.self_attn.v_proj.weight": "pytorch_model-00028-of-00034.bin",
|
| 448 |
+
"model.layers.49.input_layernorm.weight": "pytorch_model-00028-of-00034.bin",
|
| 449 |
+
"model.layers.49.mlp.down_proj.weight": "pytorch_model-00028-of-00034.bin",
|
| 450 |
+
"model.layers.49.mlp.gate_proj.weight": "pytorch_model-00028-of-00034.bin",
|
| 451 |
+
"model.layers.49.mlp.up_proj.weight": "pytorch_model-00028-of-00034.bin",
|
| 452 |
+
"model.layers.49.post_attention_layernorm.weight": "pytorch_model-00028-of-00034.bin",
|
| 453 |
+
"model.layers.49.self_attn.k_proj.weight": "pytorch_model-00028-of-00034.bin",
|
| 454 |
+
"model.layers.49.self_attn.o_proj.weight": "pytorch_model-00028-of-00034.bin",
|
| 455 |
+
"model.layers.49.self_attn.q_proj.weight": "pytorch_model-00028-of-00034.bin",
|
| 456 |
+
"model.layers.49.self_attn.rotary_emb.inv_freq": "pytorch_model-00028-of-00034.bin",
|
| 457 |
+
"model.layers.49.self_attn.v_proj.weight": "pytorch_model-00028-of-00034.bin",
|
| 458 |
+
"model.layers.5.input_layernorm.weight": "pytorch_model-00004-of-00034.bin",
|
| 459 |
+
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00004-of-00034.bin",
|
| 460 |
+
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00004-of-00034.bin",
|
| 461 |
+
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00004-of-00034.bin",
|
| 462 |
+
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00004-of-00034.bin",
|
| 463 |
+
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00004-of-00034.bin",
|
| 464 |
+
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00004-of-00034.bin",
|
| 465 |
+
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00004-of-00034.bin",
|
| 466 |
+
"model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00034.bin",
|
| 467 |
+
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00004-of-00034.bin",
|
| 468 |
+
"model.layers.50.input_layernorm.weight": "pytorch_model-00029-of-00034.bin",
|
| 469 |
+
"model.layers.50.mlp.down_proj.weight": "pytorch_model-00029-of-00034.bin",
|
| 470 |
+
"model.layers.50.mlp.gate_proj.weight": "pytorch_model-00029-of-00034.bin",
|
| 471 |
+
"model.layers.50.mlp.up_proj.weight": "pytorch_model-00029-of-00034.bin",
|
| 472 |
+
"model.layers.50.post_attention_layernorm.weight": "pytorch_model-00029-of-00034.bin",
|
| 473 |
+
"model.layers.50.self_attn.k_proj.weight": "pytorch_model-00029-of-00034.bin",
|
| 474 |
+
"model.layers.50.self_attn.o_proj.weight": "pytorch_model-00029-of-00034.bin",
|
| 475 |
+
"model.layers.50.self_attn.q_proj.weight": "pytorch_model-00029-of-00034.bin",
|
| 476 |
+
"model.layers.50.self_attn.rotary_emb.inv_freq": "pytorch_model-00029-of-00034.bin",
|
| 477 |
+
"model.layers.50.self_attn.v_proj.weight": "pytorch_model-00029-of-00034.bin",
|
| 478 |
+
"model.layers.51.input_layernorm.weight": "pytorch_model-00030-of-00034.bin",
|
| 479 |
+
"model.layers.51.mlp.down_proj.weight": "pytorch_model-00029-of-00034.bin",
|
| 480 |
+
"model.layers.51.mlp.gate_proj.weight": "pytorch_model-00029-of-00034.bin",
|
| 481 |
+
"model.layers.51.mlp.up_proj.weight": "pytorch_model-00030-of-00034.bin",
|
| 482 |
+
"model.layers.51.post_attention_layernorm.weight": "pytorch_model-00030-of-00034.bin",
|
| 483 |
+
"model.layers.51.self_attn.k_proj.weight": "pytorch_model-00029-of-00034.bin",
|
| 484 |
+
"model.layers.51.self_attn.o_proj.weight": "pytorch_model-00029-of-00034.bin",
|
| 485 |
+
"model.layers.51.self_attn.q_proj.weight": "pytorch_model-00029-of-00034.bin",
|
| 486 |
+
"model.layers.51.self_attn.rotary_emb.inv_freq": "pytorch_model-00029-of-00034.bin",
|
| 487 |
+
"model.layers.51.self_attn.v_proj.weight": "pytorch_model-00029-of-00034.bin",
|
| 488 |
+
"model.layers.52.input_layernorm.weight": "pytorch_model-00030-of-00034.bin",
|
| 489 |
+
"model.layers.52.mlp.down_proj.weight": "pytorch_model-00030-of-00034.bin",
|
| 490 |
+
"model.layers.52.mlp.gate_proj.weight": "pytorch_model-00030-of-00034.bin",
|
| 491 |
+
"model.layers.52.mlp.up_proj.weight": "pytorch_model-00030-of-00034.bin",
|
| 492 |
+
"model.layers.52.post_attention_layernorm.weight": "pytorch_model-00030-of-00034.bin",
|
| 493 |
+
"model.layers.52.self_attn.k_proj.weight": "pytorch_model-00030-of-00034.bin",
|
| 494 |
+
"model.layers.52.self_attn.o_proj.weight": "pytorch_model-00030-of-00034.bin",
|
| 495 |
+
"model.layers.52.self_attn.q_proj.weight": "pytorch_model-00030-of-00034.bin",
|
| 496 |
+
"model.layers.52.self_attn.rotary_emb.inv_freq": "pytorch_model-00030-of-00034.bin",
|
| 497 |
+
"model.layers.52.self_attn.v_proj.weight": "pytorch_model-00030-of-00034.bin",
|
| 498 |
+
"model.layers.53.input_layernorm.weight": "pytorch_model-00031-of-00034.bin",
|
| 499 |
+
"model.layers.53.mlp.down_proj.weight": "pytorch_model-00031-of-00034.bin",
|
| 500 |
+
"model.layers.53.mlp.gate_proj.weight": "pytorch_model-00030-of-00034.bin",
|
| 501 |
+
"model.layers.53.mlp.up_proj.weight": "pytorch_model-00031-of-00034.bin",
|
| 502 |
+
"model.layers.53.post_attention_layernorm.weight": "pytorch_model-00031-of-00034.bin",
|
| 503 |
+
"model.layers.53.self_attn.k_proj.weight": "pytorch_model-00030-of-00034.bin",
|
| 504 |
+
"model.layers.53.self_attn.o_proj.weight": "pytorch_model-00030-of-00034.bin",
|
| 505 |
+
"model.layers.53.self_attn.q_proj.weight": "pytorch_model-00030-of-00034.bin",
|
| 506 |
+
"model.layers.53.self_attn.rotary_emb.inv_freq": "pytorch_model-00030-of-00034.bin",
|
| 507 |
+
"model.layers.53.self_attn.v_proj.weight": "pytorch_model-00030-of-00034.bin",
|
| 508 |
+
"model.layers.54.input_layernorm.weight": "pytorch_model-00031-of-00034.bin",
|
| 509 |
+
"model.layers.54.mlp.down_proj.weight": "pytorch_model-00031-of-00034.bin",
|
| 510 |
+
"model.layers.54.mlp.gate_proj.weight": "pytorch_model-00031-of-00034.bin",
|
| 511 |
+
"model.layers.54.mlp.up_proj.weight": "pytorch_model-00031-of-00034.bin",
|
| 512 |
+
"model.layers.54.post_attention_layernorm.weight": "pytorch_model-00031-of-00034.bin",
|
| 513 |
+
"model.layers.54.self_attn.k_proj.weight": "pytorch_model-00031-of-00034.bin",
|
| 514 |
+
"model.layers.54.self_attn.o_proj.weight": "pytorch_model-00031-of-00034.bin",
|
| 515 |
+
"model.layers.54.self_attn.q_proj.weight": "pytorch_model-00031-of-00034.bin",
|
| 516 |
+
"model.layers.54.self_attn.rotary_emb.inv_freq": "pytorch_model-00031-of-00034.bin",
|
| 517 |
+
"model.layers.54.self_attn.v_proj.weight": "pytorch_model-00031-of-00034.bin",
|
| 518 |
+
"model.layers.55.input_layernorm.weight": "pytorch_model-00032-of-00034.bin",
|
| 519 |
+
"model.layers.55.mlp.down_proj.weight": "pytorch_model-00032-of-00034.bin",
|
| 520 |
+
"model.layers.55.mlp.gate_proj.weight": "pytorch_model-00032-of-00034.bin",
|
| 521 |
+
"model.layers.55.mlp.up_proj.weight": "pytorch_model-00032-of-00034.bin",
|
| 522 |
+
"model.layers.55.post_attention_layernorm.weight": "pytorch_model-00032-of-00034.bin",
|
| 523 |
+
"model.layers.55.self_attn.k_proj.weight": "pytorch_model-00031-of-00034.bin",
|
| 524 |
+
"model.layers.55.self_attn.o_proj.weight": "pytorch_model-00031-of-00034.bin",
|
| 525 |
+
"model.layers.55.self_attn.q_proj.weight": "pytorch_model-00031-of-00034.bin",
|
| 526 |
+
"model.layers.55.self_attn.rotary_emb.inv_freq": "pytorch_model-00031-of-00034.bin",
|
| 527 |
+
"model.layers.55.self_attn.v_proj.weight": "pytorch_model-00031-of-00034.bin",
|
| 528 |
+
"model.layers.56.input_layernorm.weight": "pytorch_model-00032-of-00034.bin",
|
| 529 |
+
"model.layers.56.mlp.down_proj.weight": "pytorch_model-00032-of-00034.bin",
|
| 530 |
+
"model.layers.56.mlp.gate_proj.weight": "pytorch_model-00032-of-00034.bin",
|
| 531 |
+
"model.layers.56.mlp.up_proj.weight": "pytorch_model-00032-of-00034.bin",
|
| 532 |
+
"model.layers.56.post_attention_layernorm.weight": "pytorch_model-00032-of-00034.bin",
|
| 533 |
+
"model.layers.56.self_attn.k_proj.weight": "pytorch_model-00032-of-00034.bin",
|
| 534 |
+
"model.layers.56.self_attn.o_proj.weight": "pytorch_model-00032-of-00034.bin",
|
| 535 |
+
"model.layers.56.self_attn.q_proj.weight": "pytorch_model-00032-of-00034.bin",
|
| 536 |
+
"model.layers.56.self_attn.rotary_emb.inv_freq": "pytorch_model-00032-of-00034.bin",
|
| 537 |
+
"model.layers.56.self_attn.v_proj.weight": "pytorch_model-00032-of-00034.bin",
|
| 538 |
+
"model.layers.57.input_layernorm.weight": "pytorch_model-00033-of-00034.bin",
|
| 539 |
+
"model.layers.57.mlp.down_proj.weight": "pytorch_model-00033-of-00034.bin",
|
| 540 |
+
"model.layers.57.mlp.gate_proj.weight": "pytorch_model-00033-of-00034.bin",
|
| 541 |
+
"model.layers.57.mlp.up_proj.weight": "pytorch_model-00033-of-00034.bin",
|
| 542 |
+
"model.layers.57.post_attention_layernorm.weight": "pytorch_model-00033-of-00034.bin",
|
| 543 |
+
"model.layers.57.self_attn.k_proj.weight": "pytorch_model-00032-of-00034.bin",
|
| 544 |
+
"model.layers.57.self_attn.o_proj.weight": "pytorch_model-00033-of-00034.bin",
|
| 545 |
+
"model.layers.57.self_attn.q_proj.weight": "pytorch_model-00032-of-00034.bin",
|
| 546 |
+
"model.layers.57.self_attn.rotary_emb.inv_freq": "pytorch_model-00033-of-00034.bin",
|
| 547 |
+
"model.layers.57.self_attn.v_proj.weight": "pytorch_model-00033-of-00034.bin",
|
| 548 |
+
"model.layers.58.input_layernorm.weight": "pytorch_model-00033-of-00034.bin",
|
| 549 |
+
"model.layers.58.mlp.down_proj.weight": "pytorch_model-00033-of-00034.bin",
|
| 550 |
+
"model.layers.58.mlp.gate_proj.weight": "pytorch_model-00033-of-00034.bin",
|
| 551 |
+
"model.layers.58.mlp.up_proj.weight": "pytorch_model-00033-of-00034.bin",
|
| 552 |
+
"model.layers.58.post_attention_layernorm.weight": "pytorch_model-00033-of-00034.bin",
|
| 553 |
+
"model.layers.58.self_attn.k_proj.weight": "pytorch_model-00033-of-00034.bin",
|
| 554 |
+
"model.layers.58.self_attn.o_proj.weight": "pytorch_model-00033-of-00034.bin",
|
| 555 |
+
"model.layers.58.self_attn.q_proj.weight": "pytorch_model-00033-of-00034.bin",
|
| 556 |
+
"model.layers.58.self_attn.rotary_emb.inv_freq": "pytorch_model-00033-of-00034.bin",
|
| 557 |
+
"model.layers.58.self_attn.v_proj.weight": "pytorch_model-00033-of-00034.bin",
|
| 558 |
+
"model.layers.59.input_layernorm.weight": "pytorch_model-00034-of-00034.bin",
|
| 559 |
+
"model.layers.59.mlp.down_proj.weight": "pytorch_model-00034-of-00034.bin",
|
| 560 |
+
"model.layers.59.mlp.gate_proj.weight": "pytorch_model-00034-of-00034.bin",
|
| 561 |
+
"model.layers.59.mlp.up_proj.weight": "pytorch_model-00034-of-00034.bin",
|
| 562 |
+
"model.layers.59.post_attention_layernorm.weight": "pytorch_model-00034-of-00034.bin",
|
| 563 |
+
"model.layers.59.self_attn.k_proj.weight": "pytorch_model-00034-of-00034.bin",
|
| 564 |
+
"model.layers.59.self_attn.o_proj.weight": "pytorch_model-00034-of-00034.bin",
|
| 565 |
+
"model.layers.59.self_attn.q_proj.weight": "pytorch_model-00034-of-00034.bin",
|
| 566 |
+
"model.layers.59.self_attn.rotary_emb.inv_freq": "pytorch_model-00034-of-00034.bin",
|
| 567 |
+
"model.layers.59.self_attn.v_proj.weight": "pytorch_model-00034-of-00034.bin",
|
| 568 |
+
"model.layers.6.input_layernorm.weight": "pytorch_model-00005-of-00034.bin",
|
| 569 |
+
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00004-of-00034.bin",
|
| 570 |
+
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00004-of-00034.bin",
|
| 571 |
+
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00005-of-00034.bin",
|
| 572 |
+
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00005-of-00034.bin",
|
| 573 |
+
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00004-of-00034.bin",
|
| 574 |
+
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00004-of-00034.bin",
|
| 575 |
+
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00004-of-00034.bin",
|
| 576 |
+
"model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00034.bin",
|
| 577 |
+
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00004-of-00034.bin",
|
| 578 |
+
"model.layers.7.input_layernorm.weight": "pytorch_model-00005-of-00034.bin",
|
| 579 |
+
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00005-of-00034.bin",
|
| 580 |
+
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00005-of-00034.bin",
|
| 581 |
+
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00005-of-00034.bin",
|
| 582 |
+
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00005-of-00034.bin",
|
| 583 |
+
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00005-of-00034.bin",
|
| 584 |
+
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00005-of-00034.bin",
|
| 585 |
+
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00005-of-00034.bin",
|
| 586 |
+
"model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00034.bin",
|
| 587 |
+
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00005-of-00034.bin",
|
| 588 |
+
"model.layers.8.input_layernorm.weight": "pytorch_model-00006-of-00034.bin",
|
| 589 |
+
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00006-of-00034.bin",
|
| 590 |
+
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00005-of-00034.bin",
|
| 591 |
+
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00006-of-00034.bin",
|
| 592 |
+
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00006-of-00034.bin",
|
| 593 |
+
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00005-of-00034.bin",
|
| 594 |
+
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00005-of-00034.bin",
|
| 595 |
+
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00005-of-00034.bin",
|
| 596 |
+
"model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00034.bin",
|
| 597 |
+
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00005-of-00034.bin",
|
| 598 |
+
"model.layers.9.input_layernorm.weight": "pytorch_model-00006-of-00034.bin",
|
| 599 |
+
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00006-of-00034.bin",
|
| 600 |
+
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00006-of-00034.bin",
|
| 601 |
+
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00006-of-00034.bin",
|
| 602 |
+
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00006-of-00034.bin",
|
| 603 |
+
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00006-of-00034.bin",
|
| 604 |
+
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00006-of-00034.bin",
|
| 605 |
+
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00006-of-00034.bin",
|
| 606 |
+
"model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00034.bin",
|
| 607 |
+
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00006-of-00034.bin",
|
| 608 |
+
"model.norm.weight": "pytorch_model-00034-of-00034.bin"
|
| 609 |
+
}
|
| 610 |
+
}
|