Upload with huggingface_hub
Browse files- .ipynb_checkpoints/README-checkpoint.md +42 -0
- .ipynb_checkpoints/config-checkpoint.json +24 -0
- .ipynb_checkpoints/generation_config-checkpoint.json +7 -0
- .ipynb_checkpoints/huggingface-metadata-checkpoint.txt +248 -0
- .ipynb_checkpoints/pytorch_model.bin.index-checkpoint.json +610 -0
- .ipynb_checkpoints/special_tokens_map-checkpoint.json +23 -0
- .ipynb_checkpoints/tokenizer_config-checkpoint.json +33 -0
- 4bit.safetensors +3 -0
- README.md +42 -0
- config.json +24 -0
- generation_config.json +7 -0
- huggingface-metadata.txt +248 -0
- pytorch_model.bin.index.json +610 -0
- special_tokens_map.json +23 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +33 -0
.ipynb_checkpoints/README-checkpoint.md
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Merge of [huggyllama/llama-30b](https://huggingface.co/huggyllama/llama-30b) + [kaiokendev/SuperCOT-LoRA](https://huggingface.co/kaiokendev/SuperCOT-LoRA/edit/main/README.md)
|
| 2 |
+
|
| 3 |
+
Supercot was trained to work with langchain prompting.
|
| 4 |
+
|
| 5 |
+
|
| 6 |
+
Load up locally in my custom LLM notebook that uses the Oobabooga modules to load up models: https://github.com/ausboss/Local-LLM-Langchain
|
| 7 |
+
|
| 8 |
+
Then you can add cells from of these other notebooks for testing: https://github.com/gkamradt/langchain-tutorials
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
# From Koikendev Lora page
|
| 13 |
+
|
| 14 |
+
### Compatibility
|
| 15 |
+
This LoRA is compatible with any 7B, 13B or 30B 4-bit quantized LLaMa model, including ggml quantized converted bins
|
| 16 |
+
|
| 17 |
+
### Prompting
|
| 18 |
+
You should prompt the LoRA the same way you would prompt Alpaca or Alpacino:
|
| 19 |
+
|
| 20 |
+
```
|
| 21 |
+
Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
|
| 22 |
+
|
| 23 |
+
### Instruction:
|
| 24 |
+
<instruction>
|
| 25 |
+
|
| 26 |
+
### Input:
|
| 27 |
+
<any additional context. Remove this if it's not neccesary>
|
| 28 |
+
|
| 29 |
+
### Response:
|
| 30 |
+
<make sure to leave a single new-line here for optimal results>
|
| 31 |
+
```
|
| 32 |
+
|
| 33 |
+
Remember that with lower parameter sizes, the structure of the prompt becomes more important. The same prompt worded differently can give wildly different answers. Consider using the following suggestion suffixes to improve output quality:
|
| 34 |
+
|
| 35 |
+
- "Think through this step by step"
|
| 36 |
+
- "Let's think about this logically"
|
| 37 |
+
- "Explain your reasoning"
|
| 38 |
+
- "Provide details to support your answer"
|
| 39 |
+
- "Compare and contrast your answer with alternatives"
|
| 40 |
+
|
| 41 |
+
### Coming Soon
|
| 42 |
+
- Tweet fix for 13B and 7B - lower model sizes seem to be extremely sensitive to hashtags at the end of training data responses, especially at longer cutoffs
|
.ipynb_checkpoints/config-checkpoint.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "huggyllama/llama-30b",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"bos_token_id": 1,
|
| 7 |
+
"eos_token_id": 2,
|
| 8 |
+
"hidden_act": "silu",
|
| 9 |
+
"hidden_size": 6656,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 17920,
|
| 12 |
+
"max_position_embeddings": 2048,
|
| 13 |
+
"max_sequence_length": 2048,
|
| 14 |
+
"model_type": "llama",
|
| 15 |
+
"num_attention_heads": 52,
|
| 16 |
+
"num_hidden_layers": 60,
|
| 17 |
+
"pad_token_id": 0,
|
| 18 |
+
"rms_norm_eps": 1e-06,
|
| 19 |
+
"tie_word_embeddings": false,
|
| 20 |
+
"torch_dtype": "float16",
|
| 21 |
+
"transformers_version": "4.28.0",
|
| 22 |
+
"use_cache": true,
|
| 23 |
+
"vocab_size": 32000
|
| 24 |
+
}
|
.ipynb_checkpoints/generation_config-checkpoint.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.28.0"
|
| 7 |
+
}
|
.ipynb_checkpoints/huggingface-metadata-checkpoint.txt
ADDED
|
@@ -0,0 +1,248 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
url: https://huggingface.co/ausboss/llama-30b-supercot
|
| 2 |
+
branch: main
|
| 3 |
+
download date: 2023-05-24 03:23:45
|
| 4 |
+
sha256sum:
|
| 5 |
+
09cf82059eaabd225a99bf38743c21347bd8f1afd60407fba21db30022e8275b pytorch_model-00001-of-00243.bin
|
| 6 |
+
9d058a7dc32ebfcbd3b1aa1b0cf98b8cb236c09530e06c8a1a34bfa51f940fac pytorch_model-00002-of-00243.bin
|
| 7 |
+
483ff136784e1446a1d47152ad369275b63d97ac454d45eb31bd0383de2b3be5 pytorch_model-00003-of-00243.bin
|
| 8 |
+
b5dc5c69cbd281b33441630fb502e371026415c49cc71cebdb065ebcac7b6eba pytorch_model-00004-of-00243.bin
|
| 9 |
+
38f703f231fca57a9d743fdea91bb4e052c0f0644927ec00905662a80665601c pytorch_model-00005-of-00243.bin
|
| 10 |
+
2aa57f5546e994b9259ebf08767063be4ed2512fb7e9fe98d719d3e027ebb8f4 pytorch_model-00006-of-00243.bin
|
| 11 |
+
ee40d76e5c51b5ecc279a1397afa50983b274c1bd0b145c7ae33af872a1e28d4 pytorch_model-00007-of-00243.bin
|
| 12 |
+
518c4fdaa89fa9876c3cae8ada56b7b96b0e230cb7af370308a869e4ede07395 pytorch_model-00008-of-00243.bin
|
| 13 |
+
a381bb81a90c9671940886f1afa1f1738d740bdf74f79b9849dbd1b99be616b0 pytorch_model-00009-of-00243.bin
|
| 14 |
+
0d725d67acabd07d3ca1c2d7508068d9ea763391658d35c4db3f5df4a78fd328 pytorch_model-00010-of-00243.bin
|
| 15 |
+
885fa2668e40d8c75ff4f0506f1594db76a5260bc643db5c33bda2b03c3fa640 pytorch_model-00011-of-00243.bin
|
| 16 |
+
602302d9a2e2f6e9aacc9c5593720b0366fb836a41d117f856ef936606f4c9a7 pytorch_model-00012-of-00243.bin
|
| 17 |
+
3f1fe1988509adfb8d81b2ffa2ad7061264bcbde838f58c21f05e17c63cccc01 pytorch_model-00013-of-00243.bin
|
| 18 |
+
bb699ddfd979f80d32cd8d11ac342bd598bb50a1e6d4172fb741a0e056680218 pytorch_model-00014-of-00243.bin
|
| 19 |
+
488e49dc2810cb0c8403b2891c6f81835aa6c87a3112ec83ec67368ea1740ccf pytorch_model-00015-of-00243.bin
|
| 20 |
+
615e7dd2bb66158e3079cd0fa16c4a0519c3119ab967a509763db50df62890ad pytorch_model-00016-of-00243.bin
|
| 21 |
+
ffeb25c38f3da6737a18042ea6ec758aadf1c08fa3d10f11122b956c6f62c52e pytorch_model-00017-of-00243.bin
|
| 22 |
+
899de81f2149db059c3ea2f44d9ab95e2b1632e966e22b3750b0dcb17c4f87bc pytorch_model-00018-of-00243.bin
|
| 23 |
+
e6319f1a3e67b5d2936933d58362962708d12f0cd796cb2ded83fcbaef502371 pytorch_model-00019-of-00243.bin
|
| 24 |
+
f1d0aa33e387ecdca5428e36c9be1109db674853b2871625cec6b9b6a5af4ab8 pytorch_model-00020-of-00243.bin
|
| 25 |
+
5b3ae784451facf7bc237364bb005335f3be65a266529782af9b4a114cfb2837 pytorch_model-00021-of-00243.bin
|
| 26 |
+
78726f86efadb520399f36d6bdc00388a8555ec8a9b0c7450b92e335236c4079 pytorch_model-00022-of-00243.bin
|
| 27 |
+
f4f1e3de05871c160c943ca38c26f3018a9fcd9afd1fe5d6b96c7196f5451539 pytorch_model-00023-of-00243.bin
|
| 28 |
+
58385fda4dd1ddff817078bcc304548cf1ee60dd75e23f823720c271d2b84ab2 pytorch_model-00024-of-00243.bin
|
| 29 |
+
35e7d0c3acc694ef071ffb46ce4e28a6109b0f65a3203d9ac52d3e8d4de2b8a1 pytorch_model-00025-of-00243.bin
|
| 30 |
+
f707916b73bf3e093baad418cf9030694e7b0692d0463d7df7d612d5dbae1824 pytorch_model-00026-of-00243.bin
|
| 31 |
+
272a5bd29c3067980f30ddea2b1d2299bc805b7cf2932cd60b08c26ca48620c2 pytorch_model-00027-of-00243.bin
|
| 32 |
+
3b2228ebf36f2b157154cf541ad45a95e12411d94ec8d96130816b7f77d7c4b5 pytorch_model-00028-of-00243.bin
|
| 33 |
+
d0f173c3eae5b18afa589d9f418f607ed250846830eb6360882e6de4ec7a6a9c pytorch_model-00029-of-00243.bin
|
| 34 |
+
5ed6a1d34e7309b0019c74f84d4fa1f013cbb0136388b5446997899d053daad9 pytorch_model-00030-of-00243.bin
|
| 35 |
+
83da5b0f1d756afca6beb4abd3b6ef6d54b97729d7b731e79634149eea752f1f pytorch_model-00031-of-00243.bin
|
| 36 |
+
904fa86c833bae7b562e7d6cabecbbf2f7652d9b77f5dfe63ffb1102879eca79 pytorch_model-00032-of-00243.bin
|
| 37 |
+
3ac46349de58557f72a99408f64d40475be9d762e1b92c89639b9216f374a812 pytorch_model-00033-of-00243.bin
|
| 38 |
+
a784cd0657d7f3d059da7953faf4ad031c912db84408e62e6354f3c5ac055009 pytorch_model-00034-of-00243.bin
|
| 39 |
+
af219ff22435d8331db4cce62e95dc2aff7f3d6a6f94e2412f5bd770d914d31d pytorch_model-00035-of-00243.bin
|
| 40 |
+
64f205f529359c3c7aa894afd2f92c978c189adad15621c95fdeb589c8888610 pytorch_model-00036-of-00243.bin
|
| 41 |
+
ec644a8bff8bdb6cbb90c13baf23bc4cfdf4b0c6cd061fc8a301248150764251 pytorch_model-00037-of-00243.bin
|
| 42 |
+
a0654f007170e8667204132d34414670686b13be76ff5d7e5580c4cb48e63c54 pytorch_model-00038-of-00243.bin
|
| 43 |
+
7ccbf439ef076c3ae403d668dd0660c7bdd3b0e9e2b8f94e3586a63ff2b89902 pytorch_model-00039-of-00243.bin
|
| 44 |
+
75f0735e581714ce2c4e7435dd649e3765156b5394b7bc1e6efd6cf5379c3a79 pytorch_model-00040-of-00243.bin
|
| 45 |
+
f0bc1eb8f14cc3c336665c6afe3c6f64e39960d92453db2902f1cf0813f79a11 pytorch_model-00041-of-00243.bin
|
| 46 |
+
3602e6f55f5d831429539fd0b0998d7cdcb68c337d288fa498b6cde5b8c52074 pytorch_model-00042-of-00243.bin
|
| 47 |
+
74d9d42bec0d46c04ae048068d9d9a0283a7287a39f9d73178e66768d37b226d pytorch_model-00043-of-00243.bin
|
| 48 |
+
48dd4dfd621872b4028e4ec70a3eaa768df2586865264349d70dfefb6df6d37e pytorch_model-00044-of-00243.bin
|
| 49 |
+
8adb35cb6efc3d91f53211034abd47c6a8562e9f37b85aeaad9b28511efd78fd pytorch_model-00045-of-00243.bin
|
| 50 |
+
7f4dd4b88af1d669fc20d55f1682d21728a1b68b075894436fc6f6f6007e5b4f pytorch_model-00046-of-00243.bin
|
| 51 |
+
d6a78ac519544c67c784acbdd670f68d0b7b45d9be0cf3accbb210b0505303de pytorch_model-00047-of-00243.bin
|
| 52 |
+
69d34eaaa8a48b0bbd14887b4732deaeb9038cb56299fa30dbdd66bf7cf0a004 pytorch_model-00048-of-00243.bin
|
| 53 |
+
94c49dcde09e908596928aae6839828ac087a5ad5ce9871fd24ec6889ecd53e7 pytorch_model-00049-of-00243.bin
|
| 54 |
+
0a406bdc68423623f681091482727715007a692d7740ebe0e4b29468e2062b6d pytorch_model-00050-of-00243.bin
|
| 55 |
+
b485d818f5f7bd134e3df0382ea9c7c6e372e0cadba716a91d144d090058fe62 pytorch_model-00051-of-00243.bin
|
| 56 |
+
6434295e65d4ef96baa8af71f44b44a99b47095b988de1bd48c7e8ba8a3c80be pytorch_model-00052-of-00243.bin
|
| 57 |
+
5ac66042226aee62e71e1240c095bb49a6f50b935b9797c1d36d27911e38a21f pytorch_model-00053-of-00243.bin
|
| 58 |
+
e589a0b358fcba4f5e60f6a04212e2b8641b489d1584310caf15375d2426c60d pytorch_model-00054-of-00243.bin
|
| 59 |
+
336e7c9aa81429b8bd6722857c1e442cc24449c64922e19c11ec300ab52780bb pytorch_model-00055-of-00243.bin
|
| 60 |
+
87c4c538088b0ef6c542c3b837d0981156078453f2115bf3a2c39ae7cd37f998 pytorch_model-00056-of-00243.bin
|
| 61 |
+
2d29fd39708d7cfd7d59995d0430c2cdb25f2f7ac8dd3d31f950b963d9806aa3 pytorch_model-00057-of-00243.bin
|
| 62 |
+
10c9abdf748e2aee9a3f9c56789769225ec86cc4fd00c02604a3bfb6116f7acf pytorch_model-00058-of-00243.bin
|
| 63 |
+
28f4ccf6a88a36e6e99514978f57cce70359cc32df66dde4091addc12ed6fd30 pytorch_model-00059-of-00243.bin
|
| 64 |
+
f76d024c8d574fde700a89c3e4b18fe83d2ee9c95716035b7310129cd47f5302 pytorch_model-00060-of-00243.bin
|
| 65 |
+
2918b4ab52ef985a42e29e4435bbe2f128b17c5901ca4068fb3ed34cb5555d9e pytorch_model-00061-of-00243.bin
|
| 66 |
+
ab7bfcb3aef1e67477d6f1f68e397e90b4d5c3a82903f1a13a0cccf369dcccef pytorch_model-00062-of-00243.bin
|
| 67 |
+
e944d9ecc8cfdfb0dce84f78f8707006a73f24fb8fa76a9c230123425831a184 pytorch_model-00063-of-00243.bin
|
| 68 |
+
ee20c0ec398ceab9597d104513b90336e5f4c672cbde5a3b2ece936c8a3f5148 pytorch_model-00064-of-00243.bin
|
| 69 |
+
6869b1ed0d6a2daf25939ac8ff1c696589fd62e47c114516e5726369c8e562b2 pytorch_model-00065-of-00243.bin
|
| 70 |
+
29f5ead347af64a517cb43c02140b8cca9e56831c6997709ceb92209585c9426 pytorch_model-00066-of-00243.bin
|
| 71 |
+
f3521ab2911ac86f3a8d791bd700a4cb70425f53f2639ce5d166dbf380968112 pytorch_model-00067-of-00243.bin
|
| 72 |
+
3e25fb6e55e1a627fa1bcb76c5371b8ce9b0bd233fd408a70fbc00dbb8d727c0 pytorch_model-00068-of-00243.bin
|
| 73 |
+
3e9c59b9ea19e75fe7de7ada5e41dc8c38bc95b0925eb1f41cd493d024ae6899 pytorch_model-00069-of-00243.bin
|
| 74 |
+
0aceb706fe626a8f26a52535ba9f164735aa2b9018d6f71266f07f5102bde48f pytorch_model-00070-of-00243.bin
|
| 75 |
+
43a5999497f7aee7be2f3943fb259bb283a457bbab83d08833bbc4ca55ea44d9 pytorch_model-00071-of-00243.bin
|
| 76 |
+
341304b4d0a6d8d616b6527e9a27940ff6fdff744e9d5d33648222fd788245fa pytorch_model-00072-of-00243.bin
|
| 77 |
+
ebf99e3cc61828079936a9c5b6ece50d6ca76b34f5b8e7b5544eb95771068198 pytorch_model-00073-of-00243.bin
|
| 78 |
+
afa4171a1f12702ae7ff0cdc59cae74d3211c2110a1fb4cedc9b67d5915e4519 pytorch_model-00074-of-00243.bin
|
| 79 |
+
a6980b5aa243a7c2cbd55ae561221272c32c3670f34964933f004934939eed5e pytorch_model-00075-of-00243.bin
|
| 80 |
+
c61bdce8f9252a08ecc3b4af42ee699b943ff7fe7086ca5f5c8e363ebda18d08 pytorch_model-00076-of-00243.bin
|
| 81 |
+
82139e62b584a952ef1610e251f78c9f6175d70891b7ef3240c89ca3175df5b7 pytorch_model-00077-of-00243.bin
|
| 82 |
+
0f8e26f8d0eb89d64609fe3846c3fc2b904704ce82b7b67037e4f105ea4b00e1 pytorch_model-00078-of-00243.bin
|
| 83 |
+
43a4343a8010a2e773b82a054a4b37669690a4b361d6a29eee62aa184279a22c pytorch_model-00079-of-00243.bin
|
| 84 |
+
85fc194be080bc29eace87a662f14afea9376a10b936daa89bdbc03162bfca89 pytorch_model-00080-of-00243.bin
|
| 85 |
+
016d9d5873f09d06760dabce4acb167a7115d2487fdb09a19dd0f51e195c755c pytorch_model-00081-of-00243.bin
|
| 86 |
+
fa4b253a4d70d0b6e9619fe1ca4194a64c6cdb1cc6e30e79b47a6d84068bdf52 pytorch_model-00082-of-00243.bin
|
| 87 |
+
f401abb6ebbeeaeee501f58ef182a2f0df87303e0eb3e1ef61891a564f4fe4af pytorch_model-00083-of-00243.bin
|
| 88 |
+
5565664a2f03217978813660e9ca63925e5abae9beef71b2d10772f436cdcb4e pytorch_model-00084-of-00243.bin
|
| 89 |
+
70bd36a3f6a7f45aae6e9b4b56c5889701533915d10a6b8020c93cb3ed13fb36 pytorch_model-00085-of-00243.bin
|
| 90 |
+
f0d8592e9dbadd34d090b9c309d8d2781695ecf4e6d7005addd25b13630dd611 pytorch_model-00086-of-00243.bin
|
| 91 |
+
533d20debbd4f0429f12f99ea5ce6a5b88e286af7c58604555ee7bef6c38b286 pytorch_model-00087-of-00243.bin
|
| 92 |
+
511177391ac994c00b1e39c424f8843f794c0348a9b56418c7c1584bc30d29f4 pytorch_model-00088-of-00243.bin
|
| 93 |
+
4f4c446298218fd821f5b5b9796b46650badf697fd81fa9d5af3cfa017ea2ede pytorch_model-00089-of-00243.bin
|
| 94 |
+
69935ce1a0ae99cafd3318adb16cd46005c691214d66b9c1ba2654f04bb6ee48 pytorch_model-00090-of-00243.bin
|
| 95 |
+
f8f6e703981fe6c81d09909ca4730cd50855563fc9c67804923791a19f53fe13 pytorch_model-00091-of-00243.bin
|
| 96 |
+
f4f6c8d6d43d0758840be87cf81ca1936a6ec5e7db567d7e6e28be1482ea3990 pytorch_model-00092-of-00243.bin
|
| 97 |
+
e2f13f781f5bc19ff0774b0d7d37af9ae162c372ec7b57cc6f01768349206f74 pytorch_model-00093-of-00243.bin
|
| 98 |
+
b640b907f0977649c55b5f620cefaeae0e2ab3ffa9d34004a3eaee5e5ad163e3 pytorch_model-00094-of-00243.bin
|
| 99 |
+
7028c4e1472979988f960b51b7a8872720c12e4ae77bdfc5ed2992448a497419 pytorch_model-00095-of-00243.bin
|
| 100 |
+
6c2c69a678f85a987e12eca058b60d9712f0c134fe9daf9ba45de5f8ecbf905a pytorch_model-00096-of-00243.bin
|
| 101 |
+
30747c23a557c14dca4766adedd1555529d1409045f8e8af5d8ba2912b500356 pytorch_model-00097-of-00243.bin
|
| 102 |
+
97e97a502d9354ecbc2731f93bec4b1d766636fc7b89f2be9749db719ac07400 pytorch_model-00098-of-00243.bin
|
| 103 |
+
0b7f79b28aeaddb8edcedf9ed249720c05977f13a0f7c27fe410403c0412fc0a pytorch_model-00099-of-00243.bin
|
| 104 |
+
08ebae4bfebe60c18b235bc0f6e4ee6b1659df839f1c9ddbcfad5e1398d2e923 pytorch_model-00100-of-00243.bin
|
| 105 |
+
8c8adb82ce7bef686b2cf6b64a207750249d9f725bed0b6b78249cbdd8911e48 pytorch_model-00101-of-00243.bin
|
| 106 |
+
ba24db819cf91d0f2ebc5b1ac07208cbaa71893e1cb6d8f7e0e7543173535946 pytorch_model-00102-of-00243.bin
|
| 107 |
+
74af29ea6dc24e0a1936ea080f3b70582912e0450c767a30c5360e3c62f143b9 pytorch_model-00103-of-00243.bin
|
| 108 |
+
fe068509fbae8dcfaffd178f8b830a7b3c3ddc839afff0974db4c62a701ff332 pytorch_model-00104-of-00243.bin
|
| 109 |
+
ce9f24ae56b070092e99cc119a5900b1195ad20f6a9a459a3781775f66d2266d pytorch_model-00105-of-00243.bin
|
| 110 |
+
77e7ae120c4c15a43394dcc82bdcba5fe75c844c39144d6917904111bc7cef6b pytorch_model-00106-of-00243.bin
|
| 111 |
+
dd149a6139ec2067097aebf058b4fd9b7030a49dddb8a66e323fc91000196bd6 pytorch_model-00107-of-00243.bin
|
| 112 |
+
15bc0b43afa0c818e80835fbf1e8c4213f63c0eeed1f91ed2a0c66bf9e142470 pytorch_model-00108-of-00243.bin
|
| 113 |
+
09e753f0642a1c904ef732b342894f3bd4d3f68f46989495c477eced1debde94 pytorch_model-00109-of-00243.bin
|
| 114 |
+
f3cf460b6c86e2a35fd60e3715cf9756f54c3db4bb4abc2f07c08b79002b4e19 pytorch_model-00110-of-00243.bin
|
| 115 |
+
0a353b27752a908fdc4374d041cbb5a6c912a771698d87b0f3c17874b8e488c1 pytorch_model-00111-of-00243.bin
|
| 116 |
+
63778cc7a8bc989390fd94d668c436b7ad69c86ff2f69d22f73a40bd965d3e1c pytorch_model-00112-of-00243.bin
|
| 117 |
+
11bc10f9e50374ecd18dec38dc6d0e666fb7548249bb2ec5ed67ff01778c2170 pytorch_model-00113-of-00243.bin
|
| 118 |
+
ca5885767c24be36b32cea538f90d53e05f8450224b0bb788aadd5a6dd89bd34 pytorch_model-00114-of-00243.bin
|
| 119 |
+
961620e8c9efb910851816c1dd259cb4030f529597ebc830ce539597a384b623 pytorch_model-00115-of-00243.bin
|
| 120 |
+
51ee0ac8161ccc17facabf1958ed412db37f8f5b0a190f28fe5aa16a23ade55d pytorch_model-00116-of-00243.bin
|
| 121 |
+
ad0f45f599f266e34bfaa8639b1d531744a2d841305805474c45729f0d9b777e pytorch_model-00117-of-00243.bin
|
| 122 |
+
58ac3d11f22bf981e59e856c6d78c505b0edff247e88323039a697d8d4ad57a4 pytorch_model-00118-of-00243.bin
|
| 123 |
+
1f5ab60a4639fe55130a4e8c2909c7b2e1411d8f2cbd2b00ec8341f5c9a98f06 pytorch_model-00119-of-00243.bin
|
| 124 |
+
94b4074f17ba08cfe46399d073badc2457d7ca0e3583ab690074de03ccbb62aa pytorch_model-00120-of-00243.bin
|
| 125 |
+
0a48a967e3edb8b500eaa12947a32f32f26a24b67e60d3d402afd7481df81516 pytorch_model-00121-of-00243.bin
|
| 126 |
+
fd9eb815daa468dd8be675c7248f2ff4542bbc53984562280181a01ab5a62708 pytorch_model-00122-of-00243.bin
|
| 127 |
+
fffe12cc8e0346cfc8a8230359b8ba7927294408e132218731971d90d5737b41 pytorch_model-00123-of-00243.bin
|
| 128 |
+
987380de8f157fb20e2e80aba57a8e27716e3729a736decc3758cd0d4dc73e21 pytorch_model-00124-of-00243.bin
|
| 129 |
+
6ba2b9b8a71af19c38436d7340a58fff7978575fef2deb9f89b0adb9163b2977 pytorch_model-00125-of-00243.bin
|
| 130 |
+
232f12b40cb60e6c2fb6e55bcba8a855286c16de51d1c7b0fe8c483678c04ff3 pytorch_model-00126-of-00243.bin
|
| 131 |
+
c57a3f4efb3da5660563061253fa71662e6d93e17934588eb3303691a2cb3bf3 pytorch_model-00127-of-00243.bin
|
| 132 |
+
76b14de090b4bef2c78b6ea383f18f7b6ff5dbd9dccecc55fbdfc90d71d719f3 pytorch_model-00128-of-00243.bin
|
| 133 |
+
02ff1662e0386bb56929643ff59ef8f5434277e65c5ed78fe6c78cfa68c561b0 pytorch_model-00129-of-00243.bin
|
| 134 |
+
a3e78ee0aa271f0f79b956344faca8e4f161383eb557bd1e8a5c48f26f13c5e6 pytorch_model-00130-of-00243.bin
|
| 135 |
+
01f54fd5816fc61838ec064b5cafc4c25eaa3b87937ede268b8785c426ccdd7d pytorch_model-00131-of-00243.bin
|
| 136 |
+
4ecaab016076677b83190110e275271ec4a53b3d736d945170bb1376098701ff pytorch_model-00132-of-00243.bin
|
| 137 |
+
73d18ed728d97ace5cdd89d9d0c2c76e359ceed3ad05fa03f3038b35d481db27 pytorch_model-00133-of-00243.bin
|
| 138 |
+
8b8de0770ce14282f96b36f09868aa1b8f1396f2ea2cc683e81d9b7dbdce3799 pytorch_model-00134-of-00243.bin
|
| 139 |
+
0c2e0f85e72a5e3ae5194a91edfcd141b9ebeb8654cc28769b29e79faaa7f7fe pytorch_model-00135-of-00243.bin
|
| 140 |
+
33e2206373661164a1c13008c67e2cdce7967368ebd0b2f20377ccda74723656 pytorch_model-00136-of-00243.bin
|
| 141 |
+
48d5ab98d950b69cb2807c93f97029b2019011cd7bbbc08c9f08d3390ef6f205 pytorch_model-00137-of-00243.bin
|
| 142 |
+
6435c742d6fdcbbd382d3905e46406d5af16d63d48d323301828ef8a26210fc3 pytorch_model-00138-of-00243.bin
|
| 143 |
+
c4c2593e0dcf66f315079300056c2a3f4b89c0909274bbc520e5f23cb34ad7a3 pytorch_model-00139-of-00243.bin
|
| 144 |
+
da00a68a0900c492dece277a26a9e12fae77bb1edfe32603f12c9be5ca85217a pytorch_model-00140-of-00243.bin
|
| 145 |
+
35d379ec3521bdfdb1789ad36ea80173053fcc3728c608be8760cea5805a2be2 pytorch_model-00141-of-00243.bin
|
| 146 |
+
4aba717fa9caa634aee268a2bfef4efc615a363545c23dbb997d12388b12a82d pytorch_model-00142-of-00243.bin
|
| 147 |
+
b51a06c89c8a475845c018beb6520db6ffb4a717b2bb5cb376f4e912dde124c1 pytorch_model-00143-of-00243.bin
|
| 148 |
+
ea46a5b3336bc4eb812bc1bafe1f40371585b40f5632113ca396b1064c38dd30 pytorch_model-00144-of-00243.bin
|
| 149 |
+
b346ac3f89c61c6083439c3757cedec730b672c18a35c679e08547ab873f4ecb pytorch_model-00145-of-00243.bin
|
| 150 |
+
cdf36f5445079764746a016d559d4700352e6a4e4d252d19b9d3e4b9f3552b14 pytorch_model-00146-of-00243.bin
|
| 151 |
+
6ab71611a456425ec1dee8a49f31621edb18701d876531c63ec7f19032ebaab9 pytorch_model-00147-of-00243.bin
|
| 152 |
+
530f68272df243bb3970dad56606c4f657706dfece505a7f97c4987d94c8691c pytorch_model-00148-of-00243.bin
|
| 153 |
+
3b9671d920c9506367ff83f6aa8e20c9cc3bfc955d6235e8291f200144ce1d2e pytorch_model-00149-of-00243.bin
|
| 154 |
+
cb244fe146c2e37c1a69cb2b30bf11da20082b3cad8b195e000f224764425b9a pytorch_model-00150-of-00243.bin
|
| 155 |
+
4f0bbcaabbc664e59d3a96572d0d746c2c5017c089d80ab1d6cb66047f86313e pytorch_model-00151-of-00243.bin
|
| 156 |
+
0f07bf8e97696a087a4e03db68a497ee7f8e44b8fe285717372b80e966ef6908 pytorch_model-00152-of-00243.bin
|
| 157 |
+
66ab23c030464f4b6885d54eee5189819f0399b7ce1d65cba2872f945c444c0b pytorch_model-00153-of-00243.bin
|
| 158 |
+
d10391a3fce4e7ef21a5fd041f3553b9b2b5e35c273dae79915bbec065fef613 pytorch_model-00154-of-00243.bin
|
| 159 |
+
30484b1ffc896bfa63bcd3525931821e7b984e3ceaae3a42c64d13ff92349a4e pytorch_model-00155-of-00243.bin
|
| 160 |
+
b3fd3b87151dfe5ab73598e6e48ae3331c6108e1ebbad5eecade29a6bbb314fc pytorch_model-00156-of-00243.bin
|
| 161 |
+
6a03cf30b4a4ad61a6385c6d9a169643edbfaa949459684c61f446ae361239f3 pytorch_model-00157-of-00243.bin
|
| 162 |
+
311fa925f07530e5cebcde5059bdb845db52b7f8da00623f48dc7da705a6a2df pytorch_model-00158-of-00243.bin
|
| 163 |
+
77545e68e432bacfb0bec0bc9476ad3375cfc1827da8efa9b353f9fbc758a8b8 pytorch_model-00159-of-00243.bin
|
| 164 |
+
74adb9c4554adc71b6eedc3b5a8b141b3613c1177ef0adb5bfaeeaa42bbd85a9 pytorch_model-00160-of-00243.bin
|
| 165 |
+
01b5812179799a61884ee85985ef8d8ecd00037eda2fad672dfdc2878b18a46d pytorch_model-00161-of-00243.bin
|
| 166 |
+
9650fadc97c002bbcdec1154bdd422fe12d18c61b9441ed74a1b68f545c2788b pytorch_model-00162-of-00243.bin
|
| 167 |
+
788094824dd1823f531e8cec250979556a72d22ba9d1182dbfcd3db429214b89 pytorch_model-00163-of-00243.bin
|
| 168 |
+
d755e0f69d15678a2b361212ab3d1780bf975da6d33360a5d3ed96389a02f039 pytorch_model-00164-of-00243.bin
|
| 169 |
+
5694a4c2b11ed581cdaea73cef531c26c987eedd59c221be052e8f3e443e8cfe pytorch_model-00165-of-00243.bin
|
| 170 |
+
6b0ca82e0a531a4a8f03b9ed6c5fa0c850ec1b3fd5d5f54a2c85f0e553355326 pytorch_model-00166-of-00243.bin
|
| 171 |
+
bb9afe8715554aa01b606a0b23f231b25c2762c99a2e59ca503d0e1d8b4f6a8a pytorch_model-00167-of-00243.bin
|
| 172 |
+
1c131a096d7d7363f475e6367480f5665c87111b6c58ba925474ce2ffc123799 pytorch_model-00168-of-00243.bin
|
| 173 |
+
eeaf8e409e220b251a5d9e3fac2735c13668e5da016d7c317677d4f74fe12b00 pytorch_model-00169-of-00243.bin
|
| 174 |
+
08c43e5cc128bfbbf6dd8f30e6d5bcc616c2054f341062e562927acb99922bf1 pytorch_model-00170-of-00243.bin
|
| 175 |
+
8f5b277bca1c0e05c0bd7601f4d3301d6856ff4fde62daa17a81707f60928ec5 pytorch_model-00171-of-00243.bin
|
| 176 |
+
30999caa7ced67cad5a441e3719f4ae4435a2c5591e17b08c0c2f07a18c5df5d pytorch_model-00172-of-00243.bin
|
| 177 |
+
dab1edecb2176f68468d683afe638b840f970120f9610a831c4bb5966b2f491a pytorch_model-00173-of-00243.bin
|
| 178 |
+
c82cee7ac9ecd9f6f071c244f4cf6e6e8459f8d4bb22fa38c00087195add4e6c pytorch_model-00174-of-00243.bin
|
| 179 |
+
37213a8bb345cd94e10963669f683a8c1a2378b6ff8374d863f2a09b2b0e05a1 pytorch_model-00175-of-00243.bin
|
| 180 |
+
7e80625d461a8818933861646a94e7a0d29c9ce532debea258caafb10dc4c09f pytorch_model-00176-of-00243.bin
|
| 181 |
+
4cd85828447cce382ec197771c5a4417adb37262c49c60c4440262e3c3fb45dc pytorch_model-00177-of-00243.bin
|
| 182 |
+
8c3622803909e984166c781aca5033d9fc751b76873552cdc21ec6101a371fca pytorch_model-00178-of-00243.bin
|
| 183 |
+
f7c185f4628d8ec71522b8ba2d2478d4d65d8a1de2b0f0854974929594a0cf23 pytorch_model-00179-of-00243.bin
|
| 184 |
+
a6269af0e3be281ad0b2e77fc064eadf56ff0ea50f2a1297ad93db9a76b202af pytorch_model-00180-of-00243.bin
|
| 185 |
+
b1a21ae3f3d8883734b3e8ec37eac5cc79c16a13c96e8ab945548356d0d3e447 pytorch_model-00181-of-00243.bin
|
| 186 |
+
65dfebebecac857d45e49f881b44fe52f38283da648c67b68cf8f34aaa9d7388 pytorch_model-00182-of-00243.bin
|
| 187 |
+
24dfe8116221ae9cb90ab393471d34d30f84daff0ca1632c3fc705d6c8355ba0 pytorch_model-00183-of-00243.bin
|
| 188 |
+
a02d1a5570ec7831e5c56a4e8fa9813d98415dd406f4c2fd48a3c885bdb3187b pytorch_model-00184-of-00243.bin
|
| 189 |
+
03340f30578794690dc58b97d17879f04219034f5466c4a45e3951f857c79fa1 pytorch_model-00185-of-00243.bin
|
| 190 |
+
7f5bfcc28404d85f0dffcc3ef0b014585307ade9010a004b509772b8266ec74f pytorch_model-00186-of-00243.bin
|
| 191 |
+
b3844cf4044bb1ffb02d8e9b7b1b7fd4b4c124b010c04c1f8ff8a78e03ff320f pytorch_model-00187-of-00243.bin
|
| 192 |
+
4089b0dbd91b0f2b10e7dd5fcbca4dde9faffafd661695c2da5beee8370072a3 pytorch_model-00188-of-00243.bin
|
| 193 |
+
1666768c16bfc76a11fedc3525358b9e429ae50c115b4f706960d65910715543 pytorch_model-00189-of-00243.bin
|
| 194 |
+
1affffa5fccbcc2166f666eeed7aced8d38743574ea7b6201fcd149272bb6246 pytorch_model-00190-of-00243.bin
|
| 195 |
+
ad41ac209d56068a6078429b6b18135176a9ca4ec4c24568094e1eb9ebce0f60 pytorch_model-00191-of-00243.bin
|
| 196 |
+
7ca1cab9541d33f8cbb692b5f319698c44205da210e3cdc673c9c0a2b7104b43 pytorch_model-00192-of-00243.bin
|
| 197 |
+
46d2a9a508115d14c4b4f9580a99f2b83b24222b6da6836d293f35885b610875 pytorch_model-00193-of-00243.bin
|
| 198 |
+
174844ba09a4a7471bba31188e01397be6c40e050ea685eaaa6bae22f2bb11c4 pytorch_model-00194-of-00243.bin
|
| 199 |
+
00f948d55679a438369d81791520688569c94a1b3621cb10d4454638fbcbe4db pytorch_model-00195-of-00243.bin
|
| 200 |
+
2faff3cfe1c5d530d6665a4063be2f7d26e05f0c6904cbbd7d091905d973ff79 pytorch_model-00196-of-00243.bin
|
| 201 |
+
895b6d403638393612d7d0f5cb963c80631c153f03c3d4966869057630c6f94e pytorch_model-00197-of-00243.bin
|
| 202 |
+
7dc6f3b6c479c1e775a810637d02051c8e448a8c4f6a9cd26788242dc6e515ac pytorch_model-00198-of-00243.bin
|
| 203 |
+
e0700fd25fe1be375cf7df82194120c17a154ad5c57ebfb9975f42db0aef5f48 pytorch_model-00199-of-00243.bin
|
| 204 |
+
43ea69f26fa3fc99f36a789e84022ff32a61ba3be9dac4b92e007b7361d843ca pytorch_model-00200-of-00243.bin
|
| 205 |
+
f97ffd772f8a328990d30289216d6028e6f544790af0cb81afd60205484b1c46 pytorch_model-00201-of-00243.bin
|
| 206 |
+
e1591dea37d51f02161ec7296a0787cac06d73decf4709a2ec02363ed937ddd9 pytorch_model-00202-of-00243.bin
|
| 207 |
+
ca9e94ee2efbcc51fe478068340599fca381ec4eaa40892e095ace61509e5bde pytorch_model-00203-of-00243.bin
|
| 208 |
+
37564c62aa89a31a666c3ee10dfb69bb88d6b07c2a99c0b8c16cd56913d0faf4 pytorch_model-00204-of-00243.bin
|
| 209 |
+
214824198bc777c3b026b7a164678aa7ed34a597db6fd033edaa94358395f8ae pytorch_model-00205-of-00243.bin
|
| 210 |
+
cee45752533144a37844d8eda345b613dae3f94d9da2f98f768dc3065f157a87 pytorch_model-00206-of-00243.bin
|
| 211 |
+
c9721ed5865c998b36f622f5a2c5b135fb7cd5d5e989f0ad8b6d2e9a36bce3b5 pytorch_model-00207-of-00243.bin
|
| 212 |
+
fd1323c856b7c584a0877890cd80cbddd449f4071a1180de51ac7441df33cfaf pytorch_model-00208-of-00243.bin
|
| 213 |
+
b67108c6c45e1c0426a2e890f6e15f63e5fbc9dc03b033f613b42bf7d86279ff pytorch_model-00209-of-00243.bin
|
| 214 |
+
9a3486126b67295c5533a653e354ff25b5324b8339f9d815f7ebfbca791f2378 pytorch_model-00210-of-00243.bin
|
| 215 |
+
5b624bbf42939baf3ba4d7ba25672ae363e7932d8df18b411321ea9dbab3d6c4 pytorch_model-00211-of-00243.bin
|
| 216 |
+
5005a92e9e6ccac697122bc5b8b9a0a21b4ca55e97fbe4018cfdc5fb5e869a06 pytorch_model-00212-of-00243.bin
|
| 217 |
+
ff9154478a5fd9a3b2cf5266a302497da01a538b28fbb62181d45c92d2c6c2ae pytorch_model-00213-of-00243.bin
|
| 218 |
+
4659295ce30f7ddb2c9673cf7d86280fa74869b1a08352f38406c1fbe56f51f5 pytorch_model-00214-of-00243.bin
|
| 219 |
+
794d1149608c2bb5b0007749e2474fdf7e61c150693310a1918163dbd4babfad pytorch_model-00215-of-00243.bin
|
| 220 |
+
8132b955c65d85dd5d15662ec17484143f683b78ca0af405a24725fd9393baeb pytorch_model-00216-of-00243.bin
|
| 221 |
+
640c7e2e8dca0350525ab5a51870f309b9b0203e72884be1034ef2ce74481e6e pytorch_model-00217-of-00243.bin
|
| 222 |
+
e7007217a8100f86b12894c49bac1106af5e565b03e1741b277dd02a64374fb0 pytorch_model-00218-of-00243.bin
|
| 223 |
+
c62bd6c10e27bf8d8caf92f3f13b26d92487f66a3e62f4af9e49c7eba63167b8 pytorch_model-00219-of-00243.bin
|
| 224 |
+
1e657f439b4a2db41cdaeadcdb88f5eb48a8cd726ac460da9cdefd0502b3eb9b pytorch_model-00220-of-00243.bin
|
| 225 |
+
de028b5f2a19b85c5be2d0654ae2337516220ec27669ffc8ef17c43104bb3224 pytorch_model-00221-of-00243.bin
|
| 226 |
+
3ad8fc90c1fb9bb43cfe5b2401bfb7b290ce8c704bbc5515f1ce4a5873f95139 pytorch_model-00222-of-00243.bin
|
| 227 |
+
9b989a86fa6dcf0436cc974981f6d3c8811132e92a26166a25ea457c72b3db06 pytorch_model-00223-of-00243.bin
|
| 228 |
+
aca6597466a65388286be22891e5474fd1e79eda6b2b1b3f968163a7b1a4393d pytorch_model-00224-of-00243.bin
|
| 229 |
+
fd0f867516832221d24705969d3593e5a1811ee761b8fbf7c57bcc1ad1dfc8a5 pytorch_model-00225-of-00243.bin
|
| 230 |
+
6794576954ec8970ff09499a7c0de486532326826f850bbdbf2e3fa815f69e1e pytorch_model-00226-of-00243.bin
|
| 231 |
+
4f7cef542e67021df4ff812429ea0491ef967122d94afa3cdd83b41181fa3c75 pytorch_model-00227-of-00243.bin
|
| 232 |
+
fee6c54c08d1efabc58eaa318651a625199cea878e49dd9257ec8d493009a779 pytorch_model-00228-of-00243.bin
|
| 233 |
+
ae514ec50b760014c719a16b9509b5cb3b0d9f82dfd4d489cc3d3484e8d6a9a7 pytorch_model-00229-of-00243.bin
|
| 234 |
+
6d4b7fb5ec49a09cafc0977126e0d22a7acd1f029dff96efe130c665373619f6 pytorch_model-00230-of-00243.bin
|
| 235 |
+
fcfa6ba6f24e9ae498769fd4a3e20c2f183ea290640de2f205a378d50c44c457 pytorch_model-00231-of-00243.bin
|
| 236 |
+
9f1994823e8a45ccdd4030a3abbbed28026a08fa5908ccacf7cb0f9976ad8976 pytorch_model-00232-of-00243.bin
|
| 237 |
+
cf64ed719e75ab225838749b8885e00c23b280a1c750b9f695aac00ad89152aa pytorch_model-00233-of-00243.bin
|
| 238 |
+
befc340950c3750e9fb79be5f7a3ba7ecb5bcc5422bd327e9309fb440dbbb5be pytorch_model-00234-of-00243.bin
|
| 239 |
+
abc57ae3f55a7ee8fb3fac3e36531b1e577fb4916a6b1c3fa88d7ce9969aed5f pytorch_model-00235-of-00243.bin
|
| 240 |
+
29bb9ec1e0db7a8d1dba82cfc430a6d8a6f1620dd0006a36de3a8f90cb943bac pytorch_model-00236-of-00243.bin
|
| 241 |
+
14d20d28ee07dbaba393a8d82aa17683bc31d988fb4f22d261336dd5096ae71c pytorch_model-00237-of-00243.bin
|
| 242 |
+
58df1115168fe8d60dffd81f7e0a2d5b0997601ca73f75cfab9ba128a3a3d496 pytorch_model-00238-of-00243.bin
|
| 243 |
+
7f42e2a869414c1cba14c3bb0b3e72fabc06a8a77144dac233c366c1883073b8 pytorch_model-00239-of-00243.bin
|
| 244 |
+
a4faa71e384023a2e1e21609bf5b6967925df8f2b64d825183fad2fb2418985a pytorch_model-00240-of-00243.bin
|
| 245 |
+
530296bfc60095c9f4840776a6ee24558efddcf19bd1a7ebe42895c02d7e912c pytorch_model-00241-of-00243.bin
|
| 246 |
+
8bc75fb2c6486f123c89701022ed29145c1246fe109a3defa5d470b35074a988 pytorch_model-00242-of-00243.bin
|
| 247 |
+
39f587e500e18a9db4797a87945ef84b9dc7bb989506f7d322144b270918358c pytorch_model-00243-of-00243.bin
|
| 248 |
+
9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347 tokenizer.model
|
.ipynb_checkpoints/pytorch_model.bin.index-checkpoint.json
ADDED
|
@@ -0,0 +1,610 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 65057902592
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.weight": "pytorch_model-00243-of-00243.bin",
|
| 7 |
+
"model.embed_tokens.weight": "pytorch_model-00002-of-00243.bin",
|
| 8 |
+
"model.layers.0.input_layernorm.weight": "pytorch_model-00006-of-00243.bin",
|
| 9 |
+
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00005-of-00243.bin",
|
| 10 |
+
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00004-of-00243.bin",
|
| 11 |
+
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00006-of-00243.bin",
|
| 12 |
+
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00006-of-00243.bin",
|
| 13 |
+
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00003-of-00243.bin",
|
| 14 |
+
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00003-of-00243.bin",
|
| 15 |
+
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00003-of-00243.bin",
|
| 16 |
+
"model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00243.bin",
|
| 17 |
+
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00003-of-00243.bin",
|
| 18 |
+
"model.layers.1.input_layernorm.weight": "pytorch_model-00010-of-00243.bin",
|
| 19 |
+
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00009-of-00243.bin",
|
| 20 |
+
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00008-of-00243.bin",
|
| 21 |
+
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00010-of-00243.bin",
|
| 22 |
+
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00010-of-00243.bin",
|
| 23 |
+
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00007-of-00243.bin",
|
| 24 |
+
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00007-of-00243.bin",
|
| 25 |
+
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00006-of-00243.bin",
|
| 26 |
+
"model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00243.bin",
|
| 27 |
+
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00007-of-00243.bin",
|
| 28 |
+
"model.layers.10.input_layernorm.weight": "pytorch_model-00046-of-00243.bin",
|
| 29 |
+
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00045-of-00243.bin",
|
| 30 |
+
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00044-of-00243.bin",
|
| 31 |
+
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00046-of-00243.bin",
|
| 32 |
+
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00046-of-00243.bin",
|
| 33 |
+
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00043-of-00243.bin",
|
| 34 |
+
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00043-of-00243.bin",
|
| 35 |
+
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00042-of-00243.bin",
|
| 36 |
+
"model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00043-of-00243.bin",
|
| 37 |
+
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00043-of-00243.bin",
|
| 38 |
+
"model.layers.11.input_layernorm.weight": "pytorch_model-00050-of-00243.bin",
|
| 39 |
+
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00049-of-00243.bin",
|
| 40 |
+
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00048-of-00243.bin",
|
| 41 |
+
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00050-of-00243.bin",
|
| 42 |
+
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00050-of-00243.bin",
|
| 43 |
+
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00047-of-00243.bin",
|
| 44 |
+
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00047-of-00243.bin",
|
| 45 |
+
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00046-of-00243.bin",
|
| 46 |
+
"model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00047-of-00243.bin",
|
| 47 |
+
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00047-of-00243.bin",
|
| 48 |
+
"model.layers.12.input_layernorm.weight": "pytorch_model-00054-of-00243.bin",
|
| 49 |
+
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00053-of-00243.bin",
|
| 50 |
+
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00052-of-00243.bin",
|
| 51 |
+
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00054-of-00243.bin",
|
| 52 |
+
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00054-of-00243.bin",
|
| 53 |
+
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00051-of-00243.bin",
|
| 54 |
+
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00051-of-00243.bin",
|
| 55 |
+
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00050-of-00243.bin",
|
| 56 |
+
"model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00051-of-00243.bin",
|
| 57 |
+
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00051-of-00243.bin",
|
| 58 |
+
"model.layers.13.input_layernorm.weight": "pytorch_model-00058-of-00243.bin",
|
| 59 |
+
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00057-of-00243.bin",
|
| 60 |
+
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00056-of-00243.bin",
|
| 61 |
+
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00058-of-00243.bin",
|
| 62 |
+
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00058-of-00243.bin",
|
| 63 |
+
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00055-of-00243.bin",
|
| 64 |
+
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00055-of-00243.bin",
|
| 65 |
+
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00054-of-00243.bin",
|
| 66 |
+
"model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00055-of-00243.bin",
|
| 67 |
+
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00055-of-00243.bin",
|
| 68 |
+
"model.layers.14.input_layernorm.weight": "pytorch_model-00062-of-00243.bin",
|
| 69 |
+
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00061-of-00243.bin",
|
| 70 |
+
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00060-of-00243.bin",
|
| 71 |
+
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00062-of-00243.bin",
|
| 72 |
+
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00062-of-00243.bin",
|
| 73 |
+
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00059-of-00243.bin",
|
| 74 |
+
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00059-of-00243.bin",
|
| 75 |
+
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00058-of-00243.bin",
|
| 76 |
+
"model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00059-of-00243.bin",
|
| 77 |
+
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00059-of-00243.bin",
|
| 78 |
+
"model.layers.15.input_layernorm.weight": "pytorch_model-00066-of-00243.bin",
|
| 79 |
+
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00065-of-00243.bin",
|
| 80 |
+
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00064-of-00243.bin",
|
| 81 |
+
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00066-of-00243.bin",
|
| 82 |
+
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00066-of-00243.bin",
|
| 83 |
+
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00063-of-00243.bin",
|
| 84 |
+
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00063-of-00243.bin",
|
| 85 |
+
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00062-of-00243.bin",
|
| 86 |
+
"model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00063-of-00243.bin",
|
| 87 |
+
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00063-of-00243.bin",
|
| 88 |
+
"model.layers.16.input_layernorm.weight": "pytorch_model-00070-of-00243.bin",
|
| 89 |
+
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00069-of-00243.bin",
|
| 90 |
+
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00068-of-00243.bin",
|
| 91 |
+
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00070-of-00243.bin",
|
| 92 |
+
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00070-of-00243.bin",
|
| 93 |
+
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00067-of-00243.bin",
|
| 94 |
+
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00067-of-00243.bin",
|
| 95 |
+
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00066-of-00243.bin",
|
| 96 |
+
"model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00067-of-00243.bin",
|
| 97 |
+
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00067-of-00243.bin",
|
| 98 |
+
"model.layers.17.input_layernorm.weight": "pytorch_model-00074-of-00243.bin",
|
| 99 |
+
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00073-of-00243.bin",
|
| 100 |
+
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00072-of-00243.bin",
|
| 101 |
+
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00074-of-00243.bin",
|
| 102 |
+
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00074-of-00243.bin",
|
| 103 |
+
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00071-of-00243.bin",
|
| 104 |
+
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00071-of-00243.bin",
|
| 105 |
+
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00070-of-00243.bin",
|
| 106 |
+
"model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00071-of-00243.bin",
|
| 107 |
+
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00071-of-00243.bin",
|
| 108 |
+
"model.layers.18.input_layernorm.weight": "pytorch_model-00078-of-00243.bin",
|
| 109 |
+
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00077-of-00243.bin",
|
| 110 |
+
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00076-of-00243.bin",
|
| 111 |
+
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00078-of-00243.bin",
|
| 112 |
+
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00078-of-00243.bin",
|
| 113 |
+
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00075-of-00243.bin",
|
| 114 |
+
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00075-of-00243.bin",
|
| 115 |
+
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00074-of-00243.bin",
|
| 116 |
+
"model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00075-of-00243.bin",
|
| 117 |
+
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00075-of-00243.bin",
|
| 118 |
+
"model.layers.19.input_layernorm.weight": "pytorch_model-00082-of-00243.bin",
|
| 119 |
+
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00081-of-00243.bin",
|
| 120 |
+
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00080-of-00243.bin",
|
| 121 |
+
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00082-of-00243.bin",
|
| 122 |
+
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00082-of-00243.bin",
|
| 123 |
+
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00079-of-00243.bin",
|
| 124 |
+
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00079-of-00243.bin",
|
| 125 |
+
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00078-of-00243.bin",
|
| 126 |
+
"model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00079-of-00243.bin",
|
| 127 |
+
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00079-of-00243.bin",
|
| 128 |
+
"model.layers.2.input_layernorm.weight": "pytorch_model-00014-of-00243.bin",
|
| 129 |
+
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00013-of-00243.bin",
|
| 130 |
+
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00012-of-00243.bin",
|
| 131 |
+
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00014-of-00243.bin",
|
| 132 |
+
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00014-of-00243.bin",
|
| 133 |
+
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00011-of-00243.bin",
|
| 134 |
+
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00011-of-00243.bin",
|
| 135 |
+
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00010-of-00243.bin",
|
| 136 |
+
"model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00243.bin",
|
| 137 |
+
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00011-of-00243.bin",
|
| 138 |
+
"model.layers.20.input_layernorm.weight": "pytorch_model-00086-of-00243.bin",
|
| 139 |
+
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00085-of-00243.bin",
|
| 140 |
+
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00084-of-00243.bin",
|
| 141 |
+
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00086-of-00243.bin",
|
| 142 |
+
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00086-of-00243.bin",
|
| 143 |
+
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00083-of-00243.bin",
|
| 144 |
+
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00083-of-00243.bin",
|
| 145 |
+
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00082-of-00243.bin",
|
| 146 |
+
"model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00083-of-00243.bin",
|
| 147 |
+
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00083-of-00243.bin",
|
| 148 |
+
"model.layers.21.input_layernorm.weight": "pytorch_model-00090-of-00243.bin",
|
| 149 |
+
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00089-of-00243.bin",
|
| 150 |
+
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00088-of-00243.bin",
|
| 151 |
+
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00090-of-00243.bin",
|
| 152 |
+
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00090-of-00243.bin",
|
| 153 |
+
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00087-of-00243.bin",
|
| 154 |
+
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00087-of-00243.bin",
|
| 155 |
+
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00086-of-00243.bin",
|
| 156 |
+
"model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00087-of-00243.bin",
|
| 157 |
+
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00087-of-00243.bin",
|
| 158 |
+
"model.layers.22.input_layernorm.weight": "pytorch_model-00094-of-00243.bin",
|
| 159 |
+
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00093-of-00243.bin",
|
| 160 |
+
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00092-of-00243.bin",
|
| 161 |
+
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00094-of-00243.bin",
|
| 162 |
+
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00094-of-00243.bin",
|
| 163 |
+
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00091-of-00243.bin",
|
| 164 |
+
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00091-of-00243.bin",
|
| 165 |
+
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00090-of-00243.bin",
|
| 166 |
+
"model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00091-of-00243.bin",
|
| 167 |
+
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00091-of-00243.bin",
|
| 168 |
+
"model.layers.23.input_layernorm.weight": "pytorch_model-00098-of-00243.bin",
|
| 169 |
+
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00097-of-00243.bin",
|
| 170 |
+
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00096-of-00243.bin",
|
| 171 |
+
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00098-of-00243.bin",
|
| 172 |
+
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00098-of-00243.bin",
|
| 173 |
+
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00095-of-00243.bin",
|
| 174 |
+
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00095-of-00243.bin",
|
| 175 |
+
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00094-of-00243.bin",
|
| 176 |
+
"model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00095-of-00243.bin",
|
| 177 |
+
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00095-of-00243.bin",
|
| 178 |
+
"model.layers.24.input_layernorm.weight": "pytorch_model-00102-of-00243.bin",
|
| 179 |
+
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00101-of-00243.bin",
|
| 180 |
+
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00100-of-00243.bin",
|
| 181 |
+
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00102-of-00243.bin",
|
| 182 |
+
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00102-of-00243.bin",
|
| 183 |
+
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00099-of-00243.bin",
|
| 184 |
+
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00099-of-00243.bin",
|
| 185 |
+
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00098-of-00243.bin",
|
| 186 |
+
"model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00099-of-00243.bin",
|
| 187 |
+
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00099-of-00243.bin",
|
| 188 |
+
"model.layers.25.input_layernorm.weight": "pytorch_model-00106-of-00243.bin",
|
| 189 |
+
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00105-of-00243.bin",
|
| 190 |
+
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00104-of-00243.bin",
|
| 191 |
+
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00106-of-00243.bin",
|
| 192 |
+
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00106-of-00243.bin",
|
| 193 |
+
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00103-of-00243.bin",
|
| 194 |
+
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00103-of-00243.bin",
|
| 195 |
+
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00102-of-00243.bin",
|
| 196 |
+
"model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00103-of-00243.bin",
|
| 197 |
+
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00103-of-00243.bin",
|
| 198 |
+
"model.layers.26.input_layernorm.weight": "pytorch_model-00110-of-00243.bin",
|
| 199 |
+
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00109-of-00243.bin",
|
| 200 |
+
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00108-of-00243.bin",
|
| 201 |
+
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00110-of-00243.bin",
|
| 202 |
+
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00110-of-00243.bin",
|
| 203 |
+
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00107-of-00243.bin",
|
| 204 |
+
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00107-of-00243.bin",
|
| 205 |
+
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00106-of-00243.bin",
|
| 206 |
+
"model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00107-of-00243.bin",
|
| 207 |
+
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00107-of-00243.bin",
|
| 208 |
+
"model.layers.27.input_layernorm.weight": "pytorch_model-00114-of-00243.bin",
|
| 209 |
+
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00113-of-00243.bin",
|
| 210 |
+
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00112-of-00243.bin",
|
| 211 |
+
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00114-of-00243.bin",
|
| 212 |
+
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00114-of-00243.bin",
|
| 213 |
+
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00111-of-00243.bin",
|
| 214 |
+
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00111-of-00243.bin",
|
| 215 |
+
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00110-of-00243.bin",
|
| 216 |
+
"model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00111-of-00243.bin",
|
| 217 |
+
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00111-of-00243.bin",
|
| 218 |
+
"model.layers.28.input_layernorm.weight": "pytorch_model-00118-of-00243.bin",
|
| 219 |
+
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00117-of-00243.bin",
|
| 220 |
+
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00116-of-00243.bin",
|
| 221 |
+
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00118-of-00243.bin",
|
| 222 |
+
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00118-of-00243.bin",
|
| 223 |
+
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00115-of-00243.bin",
|
| 224 |
+
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00115-of-00243.bin",
|
| 225 |
+
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00114-of-00243.bin",
|
| 226 |
+
"model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00115-of-00243.bin",
|
| 227 |
+
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00115-of-00243.bin",
|
| 228 |
+
"model.layers.29.input_layernorm.weight": "pytorch_model-00122-of-00243.bin",
|
| 229 |
+
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00121-of-00243.bin",
|
| 230 |
+
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00120-of-00243.bin",
|
| 231 |
+
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00122-of-00243.bin",
|
| 232 |
+
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00122-of-00243.bin",
|
| 233 |
+
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00119-of-00243.bin",
|
| 234 |
+
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00119-of-00243.bin",
|
| 235 |
+
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00118-of-00243.bin",
|
| 236 |
+
"model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00119-of-00243.bin",
|
| 237 |
+
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00119-of-00243.bin",
|
| 238 |
+
"model.layers.3.input_layernorm.weight": "pytorch_model-00018-of-00243.bin",
|
| 239 |
+
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00017-of-00243.bin",
|
| 240 |
+
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00016-of-00243.bin",
|
| 241 |
+
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00018-of-00243.bin",
|
| 242 |
+
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00018-of-00243.bin",
|
| 243 |
+
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00015-of-00243.bin",
|
| 244 |
+
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00015-of-00243.bin",
|
| 245 |
+
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00014-of-00243.bin",
|
| 246 |
+
"model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00015-of-00243.bin",
|
| 247 |
+
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00015-of-00243.bin",
|
| 248 |
+
"model.layers.30.input_layernorm.weight": "pytorch_model-00126-of-00243.bin",
|
| 249 |
+
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00125-of-00243.bin",
|
| 250 |
+
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00124-of-00243.bin",
|
| 251 |
+
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00126-of-00243.bin",
|
| 252 |
+
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00126-of-00243.bin",
|
| 253 |
+
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00123-of-00243.bin",
|
| 254 |
+
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00123-of-00243.bin",
|
| 255 |
+
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00122-of-00243.bin",
|
| 256 |
+
"model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00123-of-00243.bin",
|
| 257 |
+
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00123-of-00243.bin",
|
| 258 |
+
"model.layers.31.input_layernorm.weight": "pytorch_model-00130-of-00243.bin",
|
| 259 |
+
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00129-of-00243.bin",
|
| 260 |
+
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00128-of-00243.bin",
|
| 261 |
+
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00130-of-00243.bin",
|
| 262 |
+
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00130-of-00243.bin",
|
| 263 |
+
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00127-of-00243.bin",
|
| 264 |
+
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00127-of-00243.bin",
|
| 265 |
+
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00126-of-00243.bin",
|
| 266 |
+
"model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00127-of-00243.bin",
|
| 267 |
+
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00127-of-00243.bin",
|
| 268 |
+
"model.layers.32.input_layernorm.weight": "pytorch_model-00134-of-00243.bin",
|
| 269 |
+
"model.layers.32.mlp.down_proj.weight": "pytorch_model-00133-of-00243.bin",
|
| 270 |
+
"model.layers.32.mlp.gate_proj.weight": "pytorch_model-00132-of-00243.bin",
|
| 271 |
+
"model.layers.32.mlp.up_proj.weight": "pytorch_model-00134-of-00243.bin",
|
| 272 |
+
"model.layers.32.post_attention_layernorm.weight": "pytorch_model-00134-of-00243.bin",
|
| 273 |
+
"model.layers.32.self_attn.k_proj.weight": "pytorch_model-00131-of-00243.bin",
|
| 274 |
+
"model.layers.32.self_attn.o_proj.weight": "pytorch_model-00131-of-00243.bin",
|
| 275 |
+
"model.layers.32.self_attn.q_proj.weight": "pytorch_model-00130-of-00243.bin",
|
| 276 |
+
"model.layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-00131-of-00243.bin",
|
| 277 |
+
"model.layers.32.self_attn.v_proj.weight": "pytorch_model-00131-of-00243.bin",
|
| 278 |
+
"model.layers.33.input_layernorm.weight": "pytorch_model-00138-of-00243.bin",
|
| 279 |
+
"model.layers.33.mlp.down_proj.weight": "pytorch_model-00137-of-00243.bin",
|
| 280 |
+
"model.layers.33.mlp.gate_proj.weight": "pytorch_model-00136-of-00243.bin",
|
| 281 |
+
"model.layers.33.mlp.up_proj.weight": "pytorch_model-00138-of-00243.bin",
|
| 282 |
+
"model.layers.33.post_attention_layernorm.weight": "pytorch_model-00138-of-00243.bin",
|
| 283 |
+
"model.layers.33.self_attn.k_proj.weight": "pytorch_model-00135-of-00243.bin",
|
| 284 |
+
"model.layers.33.self_attn.o_proj.weight": "pytorch_model-00135-of-00243.bin",
|
| 285 |
+
"model.layers.33.self_attn.q_proj.weight": "pytorch_model-00134-of-00243.bin",
|
| 286 |
+
"model.layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-00135-of-00243.bin",
|
| 287 |
+
"model.layers.33.self_attn.v_proj.weight": "pytorch_model-00135-of-00243.bin",
|
| 288 |
+
"model.layers.34.input_layernorm.weight": "pytorch_model-00142-of-00243.bin",
|
| 289 |
+
"model.layers.34.mlp.down_proj.weight": "pytorch_model-00141-of-00243.bin",
|
| 290 |
+
"model.layers.34.mlp.gate_proj.weight": "pytorch_model-00140-of-00243.bin",
|
| 291 |
+
"model.layers.34.mlp.up_proj.weight": "pytorch_model-00142-of-00243.bin",
|
| 292 |
+
"model.layers.34.post_attention_layernorm.weight": "pytorch_model-00142-of-00243.bin",
|
| 293 |
+
"model.layers.34.self_attn.k_proj.weight": "pytorch_model-00139-of-00243.bin",
|
| 294 |
+
"model.layers.34.self_attn.o_proj.weight": "pytorch_model-00139-of-00243.bin",
|
| 295 |
+
"model.layers.34.self_attn.q_proj.weight": "pytorch_model-00138-of-00243.bin",
|
| 296 |
+
"model.layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-00139-of-00243.bin",
|
| 297 |
+
"model.layers.34.self_attn.v_proj.weight": "pytorch_model-00139-of-00243.bin",
|
| 298 |
+
"model.layers.35.input_layernorm.weight": "pytorch_model-00146-of-00243.bin",
|
| 299 |
+
"model.layers.35.mlp.down_proj.weight": "pytorch_model-00145-of-00243.bin",
|
| 300 |
+
"model.layers.35.mlp.gate_proj.weight": "pytorch_model-00144-of-00243.bin",
|
| 301 |
+
"model.layers.35.mlp.up_proj.weight": "pytorch_model-00146-of-00243.bin",
|
| 302 |
+
"model.layers.35.post_attention_layernorm.weight": "pytorch_model-00146-of-00243.bin",
|
| 303 |
+
"model.layers.35.self_attn.k_proj.weight": "pytorch_model-00143-of-00243.bin",
|
| 304 |
+
"model.layers.35.self_attn.o_proj.weight": "pytorch_model-00143-of-00243.bin",
|
| 305 |
+
"model.layers.35.self_attn.q_proj.weight": "pytorch_model-00142-of-00243.bin",
|
| 306 |
+
"model.layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-00143-of-00243.bin",
|
| 307 |
+
"model.layers.35.self_attn.v_proj.weight": "pytorch_model-00143-of-00243.bin",
|
| 308 |
+
"model.layers.36.input_layernorm.weight": "pytorch_model-00150-of-00243.bin",
|
| 309 |
+
"model.layers.36.mlp.down_proj.weight": "pytorch_model-00149-of-00243.bin",
|
| 310 |
+
"model.layers.36.mlp.gate_proj.weight": "pytorch_model-00148-of-00243.bin",
|
| 311 |
+
"model.layers.36.mlp.up_proj.weight": "pytorch_model-00150-of-00243.bin",
|
| 312 |
+
"model.layers.36.post_attention_layernorm.weight": "pytorch_model-00150-of-00243.bin",
|
| 313 |
+
"model.layers.36.self_attn.k_proj.weight": "pytorch_model-00147-of-00243.bin",
|
| 314 |
+
"model.layers.36.self_attn.o_proj.weight": "pytorch_model-00147-of-00243.bin",
|
| 315 |
+
"model.layers.36.self_attn.q_proj.weight": "pytorch_model-00146-of-00243.bin",
|
| 316 |
+
"model.layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-00147-of-00243.bin",
|
| 317 |
+
"model.layers.36.self_attn.v_proj.weight": "pytorch_model-00147-of-00243.bin",
|
| 318 |
+
"model.layers.37.input_layernorm.weight": "pytorch_model-00154-of-00243.bin",
|
| 319 |
+
"model.layers.37.mlp.down_proj.weight": "pytorch_model-00153-of-00243.bin",
|
| 320 |
+
"model.layers.37.mlp.gate_proj.weight": "pytorch_model-00152-of-00243.bin",
|
| 321 |
+
"model.layers.37.mlp.up_proj.weight": "pytorch_model-00154-of-00243.bin",
|
| 322 |
+
"model.layers.37.post_attention_layernorm.weight": "pytorch_model-00154-of-00243.bin",
|
| 323 |
+
"model.layers.37.self_attn.k_proj.weight": "pytorch_model-00151-of-00243.bin",
|
| 324 |
+
"model.layers.37.self_attn.o_proj.weight": "pytorch_model-00151-of-00243.bin",
|
| 325 |
+
"model.layers.37.self_attn.q_proj.weight": "pytorch_model-00150-of-00243.bin",
|
| 326 |
+
"model.layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-00151-of-00243.bin",
|
| 327 |
+
"model.layers.37.self_attn.v_proj.weight": "pytorch_model-00151-of-00243.bin",
|
| 328 |
+
"model.layers.38.input_layernorm.weight": "pytorch_model-00158-of-00243.bin",
|
| 329 |
+
"model.layers.38.mlp.down_proj.weight": "pytorch_model-00157-of-00243.bin",
|
| 330 |
+
"model.layers.38.mlp.gate_proj.weight": "pytorch_model-00156-of-00243.bin",
|
| 331 |
+
"model.layers.38.mlp.up_proj.weight": "pytorch_model-00158-of-00243.bin",
|
| 332 |
+
"model.layers.38.post_attention_layernorm.weight": "pytorch_model-00158-of-00243.bin",
|
| 333 |
+
"model.layers.38.self_attn.k_proj.weight": "pytorch_model-00155-of-00243.bin",
|
| 334 |
+
"model.layers.38.self_attn.o_proj.weight": "pytorch_model-00155-of-00243.bin",
|
| 335 |
+
"model.layers.38.self_attn.q_proj.weight": "pytorch_model-00154-of-00243.bin",
|
| 336 |
+
"model.layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-00155-of-00243.bin",
|
| 337 |
+
"model.layers.38.self_attn.v_proj.weight": "pytorch_model-00155-of-00243.bin",
|
| 338 |
+
"model.layers.39.input_layernorm.weight": "pytorch_model-00162-of-00243.bin",
|
| 339 |
+
"model.layers.39.mlp.down_proj.weight": "pytorch_model-00161-of-00243.bin",
|
| 340 |
+
"model.layers.39.mlp.gate_proj.weight": "pytorch_model-00160-of-00243.bin",
|
| 341 |
+
"model.layers.39.mlp.up_proj.weight": "pytorch_model-00162-of-00243.bin",
|
| 342 |
+
"model.layers.39.post_attention_layernorm.weight": "pytorch_model-00162-of-00243.bin",
|
| 343 |
+
"model.layers.39.self_attn.k_proj.weight": "pytorch_model-00159-of-00243.bin",
|
| 344 |
+
"model.layers.39.self_attn.o_proj.weight": "pytorch_model-00159-of-00243.bin",
|
| 345 |
+
"model.layers.39.self_attn.q_proj.weight": "pytorch_model-00158-of-00243.bin",
|
| 346 |
+
"model.layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-00159-of-00243.bin",
|
| 347 |
+
"model.layers.39.self_attn.v_proj.weight": "pytorch_model-00159-of-00243.bin",
|
| 348 |
+
"model.layers.4.input_layernorm.weight": "pytorch_model-00022-of-00243.bin",
|
| 349 |
+
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00021-of-00243.bin",
|
| 350 |
+
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00020-of-00243.bin",
|
| 351 |
+
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00022-of-00243.bin",
|
| 352 |
+
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00022-of-00243.bin",
|
| 353 |
+
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00019-of-00243.bin",
|
| 354 |
+
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00019-of-00243.bin",
|
| 355 |
+
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00018-of-00243.bin",
|
| 356 |
+
"model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00019-of-00243.bin",
|
| 357 |
+
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00019-of-00243.bin",
|
| 358 |
+
"model.layers.40.input_layernorm.weight": "pytorch_model-00166-of-00243.bin",
|
| 359 |
+
"model.layers.40.mlp.down_proj.weight": "pytorch_model-00165-of-00243.bin",
|
| 360 |
+
"model.layers.40.mlp.gate_proj.weight": "pytorch_model-00164-of-00243.bin",
|
| 361 |
+
"model.layers.40.mlp.up_proj.weight": "pytorch_model-00166-of-00243.bin",
|
| 362 |
+
"model.layers.40.post_attention_layernorm.weight": "pytorch_model-00166-of-00243.bin",
|
| 363 |
+
"model.layers.40.self_attn.k_proj.weight": "pytorch_model-00163-of-00243.bin",
|
| 364 |
+
"model.layers.40.self_attn.o_proj.weight": "pytorch_model-00163-of-00243.bin",
|
| 365 |
+
"model.layers.40.self_attn.q_proj.weight": "pytorch_model-00162-of-00243.bin",
|
| 366 |
+
"model.layers.40.self_attn.rotary_emb.inv_freq": "pytorch_model-00163-of-00243.bin",
|
| 367 |
+
"model.layers.40.self_attn.v_proj.weight": "pytorch_model-00163-of-00243.bin",
|
| 368 |
+
"model.layers.41.input_layernorm.weight": "pytorch_model-00170-of-00243.bin",
|
| 369 |
+
"model.layers.41.mlp.down_proj.weight": "pytorch_model-00169-of-00243.bin",
|
| 370 |
+
"model.layers.41.mlp.gate_proj.weight": "pytorch_model-00168-of-00243.bin",
|
| 371 |
+
"model.layers.41.mlp.up_proj.weight": "pytorch_model-00170-of-00243.bin",
|
| 372 |
+
"model.layers.41.post_attention_layernorm.weight": "pytorch_model-00170-of-00243.bin",
|
| 373 |
+
"model.layers.41.self_attn.k_proj.weight": "pytorch_model-00167-of-00243.bin",
|
| 374 |
+
"model.layers.41.self_attn.o_proj.weight": "pytorch_model-00167-of-00243.bin",
|
| 375 |
+
"model.layers.41.self_attn.q_proj.weight": "pytorch_model-00166-of-00243.bin",
|
| 376 |
+
"model.layers.41.self_attn.rotary_emb.inv_freq": "pytorch_model-00167-of-00243.bin",
|
| 377 |
+
"model.layers.41.self_attn.v_proj.weight": "pytorch_model-00167-of-00243.bin",
|
| 378 |
+
"model.layers.42.input_layernorm.weight": "pytorch_model-00174-of-00243.bin",
|
| 379 |
+
"model.layers.42.mlp.down_proj.weight": "pytorch_model-00173-of-00243.bin",
|
| 380 |
+
"model.layers.42.mlp.gate_proj.weight": "pytorch_model-00172-of-00243.bin",
|
| 381 |
+
"model.layers.42.mlp.up_proj.weight": "pytorch_model-00174-of-00243.bin",
|
| 382 |
+
"model.layers.42.post_attention_layernorm.weight": "pytorch_model-00174-of-00243.bin",
|
| 383 |
+
"model.layers.42.self_attn.k_proj.weight": "pytorch_model-00171-of-00243.bin",
|
| 384 |
+
"model.layers.42.self_attn.o_proj.weight": "pytorch_model-00171-of-00243.bin",
|
| 385 |
+
"model.layers.42.self_attn.q_proj.weight": "pytorch_model-00170-of-00243.bin",
|
| 386 |
+
"model.layers.42.self_attn.rotary_emb.inv_freq": "pytorch_model-00171-of-00243.bin",
|
| 387 |
+
"model.layers.42.self_attn.v_proj.weight": "pytorch_model-00171-of-00243.bin",
|
| 388 |
+
"model.layers.43.input_layernorm.weight": "pytorch_model-00178-of-00243.bin",
|
| 389 |
+
"model.layers.43.mlp.down_proj.weight": "pytorch_model-00177-of-00243.bin",
|
| 390 |
+
"model.layers.43.mlp.gate_proj.weight": "pytorch_model-00176-of-00243.bin",
|
| 391 |
+
"model.layers.43.mlp.up_proj.weight": "pytorch_model-00178-of-00243.bin",
|
| 392 |
+
"model.layers.43.post_attention_layernorm.weight": "pytorch_model-00178-of-00243.bin",
|
| 393 |
+
"model.layers.43.self_attn.k_proj.weight": "pytorch_model-00175-of-00243.bin",
|
| 394 |
+
"model.layers.43.self_attn.o_proj.weight": "pytorch_model-00175-of-00243.bin",
|
| 395 |
+
"model.layers.43.self_attn.q_proj.weight": "pytorch_model-00174-of-00243.bin",
|
| 396 |
+
"model.layers.43.self_attn.rotary_emb.inv_freq": "pytorch_model-00175-of-00243.bin",
|
| 397 |
+
"model.layers.43.self_attn.v_proj.weight": "pytorch_model-00175-of-00243.bin",
|
| 398 |
+
"model.layers.44.input_layernorm.weight": "pytorch_model-00182-of-00243.bin",
|
| 399 |
+
"model.layers.44.mlp.down_proj.weight": "pytorch_model-00181-of-00243.bin",
|
| 400 |
+
"model.layers.44.mlp.gate_proj.weight": "pytorch_model-00180-of-00243.bin",
|
| 401 |
+
"model.layers.44.mlp.up_proj.weight": "pytorch_model-00182-of-00243.bin",
|
| 402 |
+
"model.layers.44.post_attention_layernorm.weight": "pytorch_model-00182-of-00243.bin",
|
| 403 |
+
"model.layers.44.self_attn.k_proj.weight": "pytorch_model-00179-of-00243.bin",
|
| 404 |
+
"model.layers.44.self_attn.o_proj.weight": "pytorch_model-00179-of-00243.bin",
|
| 405 |
+
"model.layers.44.self_attn.q_proj.weight": "pytorch_model-00178-of-00243.bin",
|
| 406 |
+
"model.layers.44.self_attn.rotary_emb.inv_freq": "pytorch_model-00179-of-00243.bin",
|
| 407 |
+
"model.layers.44.self_attn.v_proj.weight": "pytorch_model-00179-of-00243.bin",
|
| 408 |
+
"model.layers.45.input_layernorm.weight": "pytorch_model-00186-of-00243.bin",
|
| 409 |
+
"model.layers.45.mlp.down_proj.weight": "pytorch_model-00185-of-00243.bin",
|
| 410 |
+
"model.layers.45.mlp.gate_proj.weight": "pytorch_model-00184-of-00243.bin",
|
| 411 |
+
"model.layers.45.mlp.up_proj.weight": "pytorch_model-00186-of-00243.bin",
|
| 412 |
+
"model.layers.45.post_attention_layernorm.weight": "pytorch_model-00186-of-00243.bin",
|
| 413 |
+
"model.layers.45.self_attn.k_proj.weight": "pytorch_model-00183-of-00243.bin",
|
| 414 |
+
"model.layers.45.self_attn.o_proj.weight": "pytorch_model-00183-of-00243.bin",
|
| 415 |
+
"model.layers.45.self_attn.q_proj.weight": "pytorch_model-00182-of-00243.bin",
|
| 416 |
+
"model.layers.45.self_attn.rotary_emb.inv_freq": "pytorch_model-00183-of-00243.bin",
|
| 417 |
+
"model.layers.45.self_attn.v_proj.weight": "pytorch_model-00183-of-00243.bin",
|
| 418 |
+
"model.layers.46.input_layernorm.weight": "pytorch_model-00190-of-00243.bin",
|
| 419 |
+
"model.layers.46.mlp.down_proj.weight": "pytorch_model-00189-of-00243.bin",
|
| 420 |
+
"model.layers.46.mlp.gate_proj.weight": "pytorch_model-00188-of-00243.bin",
|
| 421 |
+
"model.layers.46.mlp.up_proj.weight": "pytorch_model-00190-of-00243.bin",
|
| 422 |
+
"model.layers.46.post_attention_layernorm.weight": "pytorch_model-00190-of-00243.bin",
|
| 423 |
+
"model.layers.46.self_attn.k_proj.weight": "pytorch_model-00187-of-00243.bin",
|
| 424 |
+
"model.layers.46.self_attn.o_proj.weight": "pytorch_model-00187-of-00243.bin",
|
| 425 |
+
"model.layers.46.self_attn.q_proj.weight": "pytorch_model-00186-of-00243.bin",
|
| 426 |
+
"model.layers.46.self_attn.rotary_emb.inv_freq": "pytorch_model-00187-of-00243.bin",
|
| 427 |
+
"model.layers.46.self_attn.v_proj.weight": "pytorch_model-00187-of-00243.bin",
|
| 428 |
+
"model.layers.47.input_layernorm.weight": "pytorch_model-00194-of-00243.bin",
|
| 429 |
+
"model.layers.47.mlp.down_proj.weight": "pytorch_model-00193-of-00243.bin",
|
| 430 |
+
"model.layers.47.mlp.gate_proj.weight": "pytorch_model-00192-of-00243.bin",
|
| 431 |
+
"model.layers.47.mlp.up_proj.weight": "pytorch_model-00194-of-00243.bin",
|
| 432 |
+
"model.layers.47.post_attention_layernorm.weight": "pytorch_model-00194-of-00243.bin",
|
| 433 |
+
"model.layers.47.self_attn.k_proj.weight": "pytorch_model-00191-of-00243.bin",
|
| 434 |
+
"model.layers.47.self_attn.o_proj.weight": "pytorch_model-00191-of-00243.bin",
|
| 435 |
+
"model.layers.47.self_attn.q_proj.weight": "pytorch_model-00190-of-00243.bin",
|
| 436 |
+
"model.layers.47.self_attn.rotary_emb.inv_freq": "pytorch_model-00191-of-00243.bin",
|
| 437 |
+
"model.layers.47.self_attn.v_proj.weight": "pytorch_model-00191-of-00243.bin",
|
| 438 |
+
"model.layers.48.input_layernorm.weight": "pytorch_model-00198-of-00243.bin",
|
| 439 |
+
"model.layers.48.mlp.down_proj.weight": "pytorch_model-00197-of-00243.bin",
|
| 440 |
+
"model.layers.48.mlp.gate_proj.weight": "pytorch_model-00196-of-00243.bin",
|
| 441 |
+
"model.layers.48.mlp.up_proj.weight": "pytorch_model-00198-of-00243.bin",
|
| 442 |
+
"model.layers.48.post_attention_layernorm.weight": "pytorch_model-00198-of-00243.bin",
|
| 443 |
+
"model.layers.48.self_attn.k_proj.weight": "pytorch_model-00195-of-00243.bin",
|
| 444 |
+
"model.layers.48.self_attn.o_proj.weight": "pytorch_model-00195-of-00243.bin",
|
| 445 |
+
"model.layers.48.self_attn.q_proj.weight": "pytorch_model-00194-of-00243.bin",
|
| 446 |
+
"model.layers.48.self_attn.rotary_emb.inv_freq": "pytorch_model-00195-of-00243.bin",
|
| 447 |
+
"model.layers.48.self_attn.v_proj.weight": "pytorch_model-00195-of-00243.bin",
|
| 448 |
+
"model.layers.49.input_layernorm.weight": "pytorch_model-00202-of-00243.bin",
|
| 449 |
+
"model.layers.49.mlp.down_proj.weight": "pytorch_model-00201-of-00243.bin",
|
| 450 |
+
"model.layers.49.mlp.gate_proj.weight": "pytorch_model-00200-of-00243.bin",
|
| 451 |
+
"model.layers.49.mlp.up_proj.weight": "pytorch_model-00202-of-00243.bin",
|
| 452 |
+
"model.layers.49.post_attention_layernorm.weight": "pytorch_model-00202-of-00243.bin",
|
| 453 |
+
"model.layers.49.self_attn.k_proj.weight": "pytorch_model-00199-of-00243.bin",
|
| 454 |
+
"model.layers.49.self_attn.o_proj.weight": "pytorch_model-00199-of-00243.bin",
|
| 455 |
+
"model.layers.49.self_attn.q_proj.weight": "pytorch_model-00198-of-00243.bin",
|
| 456 |
+
"model.layers.49.self_attn.rotary_emb.inv_freq": "pytorch_model-00199-of-00243.bin",
|
| 457 |
+
"model.layers.49.self_attn.v_proj.weight": "pytorch_model-00199-of-00243.bin",
|
| 458 |
+
"model.layers.5.input_layernorm.weight": "pytorch_model-00026-of-00243.bin",
|
| 459 |
+
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00025-of-00243.bin",
|
| 460 |
+
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00024-of-00243.bin",
|
| 461 |
+
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00026-of-00243.bin",
|
| 462 |
+
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00026-of-00243.bin",
|
| 463 |
+
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00023-of-00243.bin",
|
| 464 |
+
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00023-of-00243.bin",
|
| 465 |
+
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00022-of-00243.bin",
|
| 466 |
+
"model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00023-of-00243.bin",
|
| 467 |
+
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00023-of-00243.bin",
|
| 468 |
+
"model.layers.50.input_layernorm.weight": "pytorch_model-00206-of-00243.bin",
|
| 469 |
+
"model.layers.50.mlp.down_proj.weight": "pytorch_model-00205-of-00243.bin",
|
| 470 |
+
"model.layers.50.mlp.gate_proj.weight": "pytorch_model-00204-of-00243.bin",
|
| 471 |
+
"model.layers.50.mlp.up_proj.weight": "pytorch_model-00206-of-00243.bin",
|
| 472 |
+
"model.layers.50.post_attention_layernorm.weight": "pytorch_model-00206-of-00243.bin",
|
| 473 |
+
"model.layers.50.self_attn.k_proj.weight": "pytorch_model-00203-of-00243.bin",
|
| 474 |
+
"model.layers.50.self_attn.o_proj.weight": "pytorch_model-00203-of-00243.bin",
|
| 475 |
+
"model.layers.50.self_attn.q_proj.weight": "pytorch_model-00202-of-00243.bin",
|
| 476 |
+
"model.layers.50.self_attn.rotary_emb.inv_freq": "pytorch_model-00203-of-00243.bin",
|
| 477 |
+
"model.layers.50.self_attn.v_proj.weight": "pytorch_model-00203-of-00243.bin",
|
| 478 |
+
"model.layers.51.input_layernorm.weight": "pytorch_model-00210-of-00243.bin",
|
| 479 |
+
"model.layers.51.mlp.down_proj.weight": "pytorch_model-00209-of-00243.bin",
|
| 480 |
+
"model.layers.51.mlp.gate_proj.weight": "pytorch_model-00208-of-00243.bin",
|
| 481 |
+
"model.layers.51.mlp.up_proj.weight": "pytorch_model-00210-of-00243.bin",
|
| 482 |
+
"model.layers.51.post_attention_layernorm.weight": "pytorch_model-00210-of-00243.bin",
|
| 483 |
+
"model.layers.51.self_attn.k_proj.weight": "pytorch_model-00207-of-00243.bin",
|
| 484 |
+
"model.layers.51.self_attn.o_proj.weight": "pytorch_model-00207-of-00243.bin",
|
| 485 |
+
"model.layers.51.self_attn.q_proj.weight": "pytorch_model-00206-of-00243.bin",
|
| 486 |
+
"model.layers.51.self_attn.rotary_emb.inv_freq": "pytorch_model-00207-of-00243.bin",
|
| 487 |
+
"model.layers.51.self_attn.v_proj.weight": "pytorch_model-00207-of-00243.bin",
|
| 488 |
+
"model.layers.52.input_layernorm.weight": "pytorch_model-00214-of-00243.bin",
|
| 489 |
+
"model.layers.52.mlp.down_proj.weight": "pytorch_model-00213-of-00243.bin",
|
| 490 |
+
"model.layers.52.mlp.gate_proj.weight": "pytorch_model-00212-of-00243.bin",
|
| 491 |
+
"model.layers.52.mlp.up_proj.weight": "pytorch_model-00214-of-00243.bin",
|
| 492 |
+
"model.layers.52.post_attention_layernorm.weight": "pytorch_model-00214-of-00243.bin",
|
| 493 |
+
"model.layers.52.self_attn.k_proj.weight": "pytorch_model-00211-of-00243.bin",
|
| 494 |
+
"model.layers.52.self_attn.o_proj.weight": "pytorch_model-00211-of-00243.bin",
|
| 495 |
+
"model.layers.52.self_attn.q_proj.weight": "pytorch_model-00210-of-00243.bin",
|
| 496 |
+
"model.layers.52.self_attn.rotary_emb.inv_freq": "pytorch_model-00211-of-00243.bin",
|
| 497 |
+
"model.layers.52.self_attn.v_proj.weight": "pytorch_model-00211-of-00243.bin",
|
| 498 |
+
"model.layers.53.input_layernorm.weight": "pytorch_model-00218-of-00243.bin",
|
| 499 |
+
"model.layers.53.mlp.down_proj.weight": "pytorch_model-00217-of-00243.bin",
|
| 500 |
+
"model.layers.53.mlp.gate_proj.weight": "pytorch_model-00216-of-00243.bin",
|
| 501 |
+
"model.layers.53.mlp.up_proj.weight": "pytorch_model-00218-of-00243.bin",
|
| 502 |
+
"model.layers.53.post_attention_layernorm.weight": "pytorch_model-00218-of-00243.bin",
|
| 503 |
+
"model.layers.53.self_attn.k_proj.weight": "pytorch_model-00215-of-00243.bin",
|
| 504 |
+
"model.layers.53.self_attn.o_proj.weight": "pytorch_model-00215-of-00243.bin",
|
| 505 |
+
"model.layers.53.self_attn.q_proj.weight": "pytorch_model-00214-of-00243.bin",
|
| 506 |
+
"model.layers.53.self_attn.rotary_emb.inv_freq": "pytorch_model-00215-of-00243.bin",
|
| 507 |
+
"model.layers.53.self_attn.v_proj.weight": "pytorch_model-00215-of-00243.bin",
|
| 508 |
+
"model.layers.54.input_layernorm.weight": "pytorch_model-00222-of-00243.bin",
|
| 509 |
+
"model.layers.54.mlp.down_proj.weight": "pytorch_model-00221-of-00243.bin",
|
| 510 |
+
"model.layers.54.mlp.gate_proj.weight": "pytorch_model-00220-of-00243.bin",
|
| 511 |
+
"model.layers.54.mlp.up_proj.weight": "pytorch_model-00222-of-00243.bin",
|
| 512 |
+
"model.layers.54.post_attention_layernorm.weight": "pytorch_model-00222-of-00243.bin",
|
| 513 |
+
"model.layers.54.self_attn.k_proj.weight": "pytorch_model-00219-of-00243.bin",
|
| 514 |
+
"model.layers.54.self_attn.o_proj.weight": "pytorch_model-00219-of-00243.bin",
|
| 515 |
+
"model.layers.54.self_attn.q_proj.weight": "pytorch_model-00218-of-00243.bin",
|
| 516 |
+
"model.layers.54.self_attn.rotary_emb.inv_freq": "pytorch_model-00219-of-00243.bin",
|
| 517 |
+
"model.layers.54.self_attn.v_proj.weight": "pytorch_model-00219-of-00243.bin",
|
| 518 |
+
"model.layers.55.input_layernorm.weight": "pytorch_model-00226-of-00243.bin",
|
| 519 |
+
"model.layers.55.mlp.down_proj.weight": "pytorch_model-00225-of-00243.bin",
|
| 520 |
+
"model.layers.55.mlp.gate_proj.weight": "pytorch_model-00224-of-00243.bin",
|
| 521 |
+
"model.layers.55.mlp.up_proj.weight": "pytorch_model-00226-of-00243.bin",
|
| 522 |
+
"model.layers.55.post_attention_layernorm.weight": "pytorch_model-00226-of-00243.bin",
|
| 523 |
+
"model.layers.55.self_attn.k_proj.weight": "pytorch_model-00223-of-00243.bin",
|
| 524 |
+
"model.layers.55.self_attn.o_proj.weight": "pytorch_model-00223-of-00243.bin",
|
| 525 |
+
"model.layers.55.self_attn.q_proj.weight": "pytorch_model-00222-of-00243.bin",
|
| 526 |
+
"model.layers.55.self_attn.rotary_emb.inv_freq": "pytorch_model-00223-of-00243.bin",
|
| 527 |
+
"model.layers.55.self_attn.v_proj.weight": "pytorch_model-00223-of-00243.bin",
|
| 528 |
+
"model.layers.56.input_layernorm.weight": "pytorch_model-00230-of-00243.bin",
|
| 529 |
+
"model.layers.56.mlp.down_proj.weight": "pytorch_model-00229-of-00243.bin",
|
| 530 |
+
"model.layers.56.mlp.gate_proj.weight": "pytorch_model-00228-of-00243.bin",
|
| 531 |
+
"model.layers.56.mlp.up_proj.weight": "pytorch_model-00230-of-00243.bin",
|
| 532 |
+
"model.layers.56.post_attention_layernorm.weight": "pytorch_model-00230-of-00243.bin",
|
| 533 |
+
"model.layers.56.self_attn.k_proj.weight": "pytorch_model-00227-of-00243.bin",
|
| 534 |
+
"model.layers.56.self_attn.o_proj.weight": "pytorch_model-00227-of-00243.bin",
|
| 535 |
+
"model.layers.56.self_attn.q_proj.weight": "pytorch_model-00226-of-00243.bin",
|
| 536 |
+
"model.layers.56.self_attn.rotary_emb.inv_freq": "pytorch_model-00227-of-00243.bin",
|
| 537 |
+
"model.layers.56.self_attn.v_proj.weight": "pytorch_model-00227-of-00243.bin",
|
| 538 |
+
"model.layers.57.input_layernorm.weight": "pytorch_model-00234-of-00243.bin",
|
| 539 |
+
"model.layers.57.mlp.down_proj.weight": "pytorch_model-00233-of-00243.bin",
|
| 540 |
+
"model.layers.57.mlp.gate_proj.weight": "pytorch_model-00232-of-00243.bin",
|
| 541 |
+
"model.layers.57.mlp.up_proj.weight": "pytorch_model-00234-of-00243.bin",
|
| 542 |
+
"model.layers.57.post_attention_layernorm.weight": "pytorch_model-00234-of-00243.bin",
|
| 543 |
+
"model.layers.57.self_attn.k_proj.weight": "pytorch_model-00231-of-00243.bin",
|
| 544 |
+
"model.layers.57.self_attn.o_proj.weight": "pytorch_model-00231-of-00243.bin",
|
| 545 |
+
"model.layers.57.self_attn.q_proj.weight": "pytorch_model-00230-of-00243.bin",
|
| 546 |
+
"model.layers.57.self_attn.rotary_emb.inv_freq": "pytorch_model-00231-of-00243.bin",
|
| 547 |
+
"model.layers.57.self_attn.v_proj.weight": "pytorch_model-00231-of-00243.bin",
|
| 548 |
+
"model.layers.58.input_layernorm.weight": "pytorch_model-00238-of-00243.bin",
|
| 549 |
+
"model.layers.58.mlp.down_proj.weight": "pytorch_model-00237-of-00243.bin",
|
| 550 |
+
"model.layers.58.mlp.gate_proj.weight": "pytorch_model-00236-of-00243.bin",
|
| 551 |
+
"model.layers.58.mlp.up_proj.weight": "pytorch_model-00238-of-00243.bin",
|
| 552 |
+
"model.layers.58.post_attention_layernorm.weight": "pytorch_model-00238-of-00243.bin",
|
| 553 |
+
"model.layers.58.self_attn.k_proj.weight": "pytorch_model-00235-of-00243.bin",
|
| 554 |
+
"model.layers.58.self_attn.o_proj.weight": "pytorch_model-00235-of-00243.bin",
|
| 555 |
+
"model.layers.58.self_attn.q_proj.weight": "pytorch_model-00234-of-00243.bin",
|
| 556 |
+
"model.layers.58.self_attn.rotary_emb.inv_freq": "pytorch_model-00235-of-00243.bin",
|
| 557 |
+
"model.layers.58.self_attn.v_proj.weight": "pytorch_model-00235-of-00243.bin",
|
| 558 |
+
"model.layers.59.input_layernorm.weight": "pytorch_model-00242-of-00243.bin",
|
| 559 |
+
"model.layers.59.mlp.down_proj.weight": "pytorch_model-00241-of-00243.bin",
|
| 560 |
+
"model.layers.59.mlp.gate_proj.weight": "pytorch_model-00240-of-00243.bin",
|
| 561 |
+
"model.layers.59.mlp.up_proj.weight": "pytorch_model-00242-of-00243.bin",
|
| 562 |
+
"model.layers.59.post_attention_layernorm.weight": "pytorch_model-00242-of-00243.bin",
|
| 563 |
+
"model.layers.59.self_attn.k_proj.weight": "pytorch_model-00239-of-00243.bin",
|
| 564 |
+
"model.layers.59.self_attn.o_proj.weight": "pytorch_model-00239-of-00243.bin",
|
| 565 |
+
"model.layers.59.self_attn.q_proj.weight": "pytorch_model-00238-of-00243.bin",
|
| 566 |
+
"model.layers.59.self_attn.rotary_emb.inv_freq": "pytorch_model-00239-of-00243.bin",
|
| 567 |
+
"model.layers.59.self_attn.v_proj.weight": "pytorch_model-00239-of-00243.bin",
|
| 568 |
+
"model.layers.6.input_layernorm.weight": "pytorch_model-00030-of-00243.bin",
|
| 569 |
+
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00029-of-00243.bin",
|
| 570 |
+
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00028-of-00243.bin",
|
| 571 |
+
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00030-of-00243.bin",
|
| 572 |
+
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00030-of-00243.bin",
|
| 573 |
+
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00027-of-00243.bin",
|
| 574 |
+
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00027-of-00243.bin",
|
| 575 |
+
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00026-of-00243.bin",
|
| 576 |
+
"model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00027-of-00243.bin",
|
| 577 |
+
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00027-of-00243.bin",
|
| 578 |
+
"model.layers.7.input_layernorm.weight": "pytorch_model-00034-of-00243.bin",
|
| 579 |
+
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00033-of-00243.bin",
|
| 580 |
+
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00032-of-00243.bin",
|
| 581 |
+
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00034-of-00243.bin",
|
| 582 |
+
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00034-of-00243.bin",
|
| 583 |
+
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00031-of-00243.bin",
|
| 584 |
+
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00031-of-00243.bin",
|
| 585 |
+
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00030-of-00243.bin",
|
| 586 |
+
"model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00031-of-00243.bin",
|
| 587 |
+
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00031-of-00243.bin",
|
| 588 |
+
"model.layers.8.input_layernorm.weight": "pytorch_model-00038-of-00243.bin",
|
| 589 |
+
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00037-of-00243.bin",
|
| 590 |
+
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00036-of-00243.bin",
|
| 591 |
+
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00038-of-00243.bin",
|
| 592 |
+
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00038-of-00243.bin",
|
| 593 |
+
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00035-of-00243.bin",
|
| 594 |
+
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00035-of-00243.bin",
|
| 595 |
+
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00034-of-00243.bin",
|
| 596 |
+
"model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00035-of-00243.bin",
|
| 597 |
+
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00035-of-00243.bin",
|
| 598 |
+
"model.layers.9.input_layernorm.weight": "pytorch_model-00042-of-00243.bin",
|
| 599 |
+
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00041-of-00243.bin",
|
| 600 |
+
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00040-of-00243.bin",
|
| 601 |
+
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00042-of-00243.bin",
|
| 602 |
+
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00042-of-00243.bin",
|
| 603 |
+
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00039-of-00243.bin",
|
| 604 |
+
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00039-of-00243.bin",
|
| 605 |
+
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00038-of-00243.bin",
|
| 606 |
+
"model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00039-of-00243.bin",
|
| 607 |
+
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00039-of-00243.bin",
|
| 608 |
+
"model.norm.weight": "pytorch_model-00242-of-00243.bin"
|
| 609 |
+
}
|
| 610 |
+
}
|
.ipynb_checkpoints/special_tokens_map-checkpoint.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"unk_token": {
|
| 17 |
+
"content": "<unk>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
.ipynb_checkpoints/tokenizer_config-checkpoint.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"bos_token": {
|
| 5 |
+
"__type": "AddedToken",
|
| 6 |
+
"content": "<s>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": true,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"clean_up_tokenization_spaces": false,
|
| 13 |
+
"eos_token": {
|
| 14 |
+
"__type": "AddedToken",
|
| 15 |
+
"content": "</s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": true,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false
|
| 20 |
+
},
|
| 21 |
+
"model_max_length": 2048,
|
| 22 |
+
"pad_token": null,
|
| 23 |
+
"sp_model_kwargs": {},
|
| 24 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 25 |
+
"unk_token": {
|
| 26 |
+
"__type": "AddedToken",
|
| 27 |
+
"content": "<unk>",
|
| 28 |
+
"lstrip": false,
|
| 29 |
+
"normalized": true,
|
| 30 |
+
"rstrip": false,
|
| 31 |
+
"single_word": false
|
| 32 |
+
}
|
| 33 |
+
}
|
4bit.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7a8db3fbb9af7b86d2742aad0aea95773bca7529aa03ef06f737a1ef0b8998e6
|
| 3 |
+
size 16940128404
|
README.md
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Merge of [huggyllama/llama-30b](https://huggingface.co/huggyllama/llama-30b) + [kaiokendev/SuperCOT-LoRA](https://huggingface.co/kaiokendev/SuperCOT-LoRA/edit/main/README.md)
|
| 2 |
+
|
| 3 |
+
Supercot was trained to work with langchain prompting.
|
| 4 |
+
|
| 5 |
+
|
| 6 |
+
Load up locally in my custom LLM notebook that uses the Oobabooga modules to load up models: https://github.com/ausboss/Local-LLM-Langchain
|
| 7 |
+
|
| 8 |
+
Then you can add cells from of these other notebooks for testing: https://github.com/gkamradt/langchain-tutorials
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
# From Koikendev Lora page
|
| 13 |
+
|
| 14 |
+
### Compatibility
|
| 15 |
+
This LoRA is compatible with any 7B, 13B or 30B 4-bit quantized LLaMa model, including ggml quantized converted bins
|
| 16 |
+
|
| 17 |
+
### Prompting
|
| 18 |
+
You should prompt the LoRA the same way you would prompt Alpaca or Alpacino:
|
| 19 |
+
|
| 20 |
+
```
|
| 21 |
+
Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
|
| 22 |
+
|
| 23 |
+
### Instruction:
|
| 24 |
+
<instruction>
|
| 25 |
+
|
| 26 |
+
### Input:
|
| 27 |
+
<any additional context. Remove this if it's not neccesary>
|
| 28 |
+
|
| 29 |
+
### Response:
|
| 30 |
+
<make sure to leave a single new-line here for optimal results>
|
| 31 |
+
```
|
| 32 |
+
|
| 33 |
+
Remember that with lower parameter sizes, the structure of the prompt becomes more important. The same prompt worded differently can give wildly different answers. Consider using the following suggestion suffixes to improve output quality:
|
| 34 |
+
|
| 35 |
+
- "Think through this step by step"
|
| 36 |
+
- "Let's think about this logically"
|
| 37 |
+
- "Explain your reasoning"
|
| 38 |
+
- "Provide details to support your answer"
|
| 39 |
+
- "Compare and contrast your answer with alternatives"
|
| 40 |
+
|
| 41 |
+
### Coming Soon
|
| 42 |
+
- Tweet fix for 13B and 7B - lower model sizes seem to be extremely sensitive to hashtags at the end of training data responses, especially at longer cutoffs
|
config.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "huggyllama/llama-30b",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"bos_token_id": 1,
|
| 7 |
+
"eos_token_id": 2,
|
| 8 |
+
"hidden_act": "silu",
|
| 9 |
+
"hidden_size": 6656,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 17920,
|
| 12 |
+
"max_position_embeddings": 2048,
|
| 13 |
+
"max_sequence_length": 2048,
|
| 14 |
+
"model_type": "llama",
|
| 15 |
+
"num_attention_heads": 52,
|
| 16 |
+
"num_hidden_layers": 60,
|
| 17 |
+
"pad_token_id": 0,
|
| 18 |
+
"rms_norm_eps": 1e-06,
|
| 19 |
+
"tie_word_embeddings": false,
|
| 20 |
+
"torch_dtype": "float16",
|
| 21 |
+
"transformers_version": "4.28.0",
|
| 22 |
+
"use_cache": true,
|
| 23 |
+
"vocab_size": 32000
|
| 24 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.28.0"
|
| 7 |
+
}
|
huggingface-metadata.txt
ADDED
|
@@ -0,0 +1,248 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
url: https://huggingface.co/ausboss/llama-30b-supercot
|
| 2 |
+
branch: main
|
| 3 |
+
download date: 2023-05-24 03:23:45
|
| 4 |
+
sha256sum:
|
| 5 |
+
09cf82059eaabd225a99bf38743c21347bd8f1afd60407fba21db30022e8275b pytorch_model-00001-of-00243.bin
|
| 6 |
+
9d058a7dc32ebfcbd3b1aa1b0cf98b8cb236c09530e06c8a1a34bfa51f940fac pytorch_model-00002-of-00243.bin
|
| 7 |
+
483ff136784e1446a1d47152ad369275b63d97ac454d45eb31bd0383de2b3be5 pytorch_model-00003-of-00243.bin
|
| 8 |
+
b5dc5c69cbd281b33441630fb502e371026415c49cc71cebdb065ebcac7b6eba pytorch_model-00004-of-00243.bin
|
| 9 |
+
38f703f231fca57a9d743fdea91bb4e052c0f0644927ec00905662a80665601c pytorch_model-00005-of-00243.bin
|
| 10 |
+
2aa57f5546e994b9259ebf08767063be4ed2512fb7e9fe98d719d3e027ebb8f4 pytorch_model-00006-of-00243.bin
|
| 11 |
+
ee40d76e5c51b5ecc279a1397afa50983b274c1bd0b145c7ae33af872a1e28d4 pytorch_model-00007-of-00243.bin
|
| 12 |
+
518c4fdaa89fa9876c3cae8ada56b7b96b0e230cb7af370308a869e4ede07395 pytorch_model-00008-of-00243.bin
|
| 13 |
+
a381bb81a90c9671940886f1afa1f1738d740bdf74f79b9849dbd1b99be616b0 pytorch_model-00009-of-00243.bin
|
| 14 |
+
0d725d67acabd07d3ca1c2d7508068d9ea763391658d35c4db3f5df4a78fd328 pytorch_model-00010-of-00243.bin
|
| 15 |
+
885fa2668e40d8c75ff4f0506f1594db76a5260bc643db5c33bda2b03c3fa640 pytorch_model-00011-of-00243.bin
|
| 16 |
+
602302d9a2e2f6e9aacc9c5593720b0366fb836a41d117f856ef936606f4c9a7 pytorch_model-00012-of-00243.bin
|
| 17 |
+
3f1fe1988509adfb8d81b2ffa2ad7061264bcbde838f58c21f05e17c63cccc01 pytorch_model-00013-of-00243.bin
|
| 18 |
+
bb699ddfd979f80d32cd8d11ac342bd598bb50a1e6d4172fb741a0e056680218 pytorch_model-00014-of-00243.bin
|
| 19 |
+
488e49dc2810cb0c8403b2891c6f81835aa6c87a3112ec83ec67368ea1740ccf pytorch_model-00015-of-00243.bin
|
| 20 |
+
615e7dd2bb66158e3079cd0fa16c4a0519c3119ab967a509763db50df62890ad pytorch_model-00016-of-00243.bin
|
| 21 |
+
ffeb25c38f3da6737a18042ea6ec758aadf1c08fa3d10f11122b956c6f62c52e pytorch_model-00017-of-00243.bin
|
| 22 |
+
899de81f2149db059c3ea2f44d9ab95e2b1632e966e22b3750b0dcb17c4f87bc pytorch_model-00018-of-00243.bin
|
| 23 |
+
e6319f1a3e67b5d2936933d58362962708d12f0cd796cb2ded83fcbaef502371 pytorch_model-00019-of-00243.bin
|
| 24 |
+
f1d0aa33e387ecdca5428e36c9be1109db674853b2871625cec6b9b6a5af4ab8 pytorch_model-00020-of-00243.bin
|
| 25 |
+
5b3ae784451facf7bc237364bb005335f3be65a266529782af9b4a114cfb2837 pytorch_model-00021-of-00243.bin
|
| 26 |
+
78726f86efadb520399f36d6bdc00388a8555ec8a9b0c7450b92e335236c4079 pytorch_model-00022-of-00243.bin
|
| 27 |
+
f4f1e3de05871c160c943ca38c26f3018a9fcd9afd1fe5d6b96c7196f5451539 pytorch_model-00023-of-00243.bin
|
| 28 |
+
58385fda4dd1ddff817078bcc304548cf1ee60dd75e23f823720c271d2b84ab2 pytorch_model-00024-of-00243.bin
|
| 29 |
+
35e7d0c3acc694ef071ffb46ce4e28a6109b0f65a3203d9ac52d3e8d4de2b8a1 pytorch_model-00025-of-00243.bin
|
| 30 |
+
f707916b73bf3e093baad418cf9030694e7b0692d0463d7df7d612d5dbae1824 pytorch_model-00026-of-00243.bin
|
| 31 |
+
272a5bd29c3067980f30ddea2b1d2299bc805b7cf2932cd60b08c26ca48620c2 pytorch_model-00027-of-00243.bin
|
| 32 |
+
3b2228ebf36f2b157154cf541ad45a95e12411d94ec8d96130816b7f77d7c4b5 pytorch_model-00028-of-00243.bin
|
| 33 |
+
d0f173c3eae5b18afa589d9f418f607ed250846830eb6360882e6de4ec7a6a9c pytorch_model-00029-of-00243.bin
|
| 34 |
+
5ed6a1d34e7309b0019c74f84d4fa1f013cbb0136388b5446997899d053daad9 pytorch_model-00030-of-00243.bin
|
| 35 |
+
83da5b0f1d756afca6beb4abd3b6ef6d54b97729d7b731e79634149eea752f1f pytorch_model-00031-of-00243.bin
|
| 36 |
+
904fa86c833bae7b562e7d6cabecbbf2f7652d9b77f5dfe63ffb1102879eca79 pytorch_model-00032-of-00243.bin
|
| 37 |
+
3ac46349de58557f72a99408f64d40475be9d762e1b92c89639b9216f374a812 pytorch_model-00033-of-00243.bin
|
| 38 |
+
a784cd0657d7f3d059da7953faf4ad031c912db84408e62e6354f3c5ac055009 pytorch_model-00034-of-00243.bin
|
| 39 |
+
af219ff22435d8331db4cce62e95dc2aff7f3d6a6f94e2412f5bd770d914d31d pytorch_model-00035-of-00243.bin
|
| 40 |
+
64f205f529359c3c7aa894afd2f92c978c189adad15621c95fdeb589c8888610 pytorch_model-00036-of-00243.bin
|
| 41 |
+
ec644a8bff8bdb6cbb90c13baf23bc4cfdf4b0c6cd061fc8a301248150764251 pytorch_model-00037-of-00243.bin
|
| 42 |
+
a0654f007170e8667204132d34414670686b13be76ff5d7e5580c4cb48e63c54 pytorch_model-00038-of-00243.bin
|
| 43 |
+
7ccbf439ef076c3ae403d668dd0660c7bdd3b0e9e2b8f94e3586a63ff2b89902 pytorch_model-00039-of-00243.bin
|
| 44 |
+
75f0735e581714ce2c4e7435dd649e3765156b5394b7bc1e6efd6cf5379c3a79 pytorch_model-00040-of-00243.bin
|
| 45 |
+
f0bc1eb8f14cc3c336665c6afe3c6f64e39960d92453db2902f1cf0813f79a11 pytorch_model-00041-of-00243.bin
|
| 46 |
+
3602e6f55f5d831429539fd0b0998d7cdcb68c337d288fa498b6cde5b8c52074 pytorch_model-00042-of-00243.bin
|
| 47 |
+
74d9d42bec0d46c04ae048068d9d9a0283a7287a39f9d73178e66768d37b226d pytorch_model-00043-of-00243.bin
|
| 48 |
+
48dd4dfd621872b4028e4ec70a3eaa768df2586865264349d70dfefb6df6d37e pytorch_model-00044-of-00243.bin
|
| 49 |
+
8adb35cb6efc3d91f53211034abd47c6a8562e9f37b85aeaad9b28511efd78fd pytorch_model-00045-of-00243.bin
|
| 50 |
+
7f4dd4b88af1d669fc20d55f1682d21728a1b68b075894436fc6f6f6007e5b4f pytorch_model-00046-of-00243.bin
|
| 51 |
+
d6a78ac519544c67c784acbdd670f68d0b7b45d9be0cf3accbb210b0505303de pytorch_model-00047-of-00243.bin
|
| 52 |
+
69d34eaaa8a48b0bbd14887b4732deaeb9038cb56299fa30dbdd66bf7cf0a004 pytorch_model-00048-of-00243.bin
|
| 53 |
+
94c49dcde09e908596928aae6839828ac087a5ad5ce9871fd24ec6889ecd53e7 pytorch_model-00049-of-00243.bin
|
| 54 |
+
0a406bdc68423623f681091482727715007a692d7740ebe0e4b29468e2062b6d pytorch_model-00050-of-00243.bin
|
| 55 |
+
b485d818f5f7bd134e3df0382ea9c7c6e372e0cadba716a91d144d090058fe62 pytorch_model-00051-of-00243.bin
|
| 56 |
+
6434295e65d4ef96baa8af71f44b44a99b47095b988de1bd48c7e8ba8a3c80be pytorch_model-00052-of-00243.bin
|
| 57 |
+
5ac66042226aee62e71e1240c095bb49a6f50b935b9797c1d36d27911e38a21f pytorch_model-00053-of-00243.bin
|
| 58 |
+
e589a0b358fcba4f5e60f6a04212e2b8641b489d1584310caf15375d2426c60d pytorch_model-00054-of-00243.bin
|
| 59 |
+
336e7c9aa81429b8bd6722857c1e442cc24449c64922e19c11ec300ab52780bb pytorch_model-00055-of-00243.bin
|
| 60 |
+
87c4c538088b0ef6c542c3b837d0981156078453f2115bf3a2c39ae7cd37f998 pytorch_model-00056-of-00243.bin
|
| 61 |
+
2d29fd39708d7cfd7d59995d0430c2cdb25f2f7ac8dd3d31f950b963d9806aa3 pytorch_model-00057-of-00243.bin
|
| 62 |
+
10c9abdf748e2aee9a3f9c56789769225ec86cc4fd00c02604a3bfb6116f7acf pytorch_model-00058-of-00243.bin
|
| 63 |
+
28f4ccf6a88a36e6e99514978f57cce70359cc32df66dde4091addc12ed6fd30 pytorch_model-00059-of-00243.bin
|
| 64 |
+
f76d024c8d574fde700a89c3e4b18fe83d2ee9c95716035b7310129cd47f5302 pytorch_model-00060-of-00243.bin
|
| 65 |
+
2918b4ab52ef985a42e29e4435bbe2f128b17c5901ca4068fb3ed34cb5555d9e pytorch_model-00061-of-00243.bin
|
| 66 |
+
ab7bfcb3aef1e67477d6f1f68e397e90b4d5c3a82903f1a13a0cccf369dcccef pytorch_model-00062-of-00243.bin
|
| 67 |
+
e944d9ecc8cfdfb0dce84f78f8707006a73f24fb8fa76a9c230123425831a184 pytorch_model-00063-of-00243.bin
|
| 68 |
+
ee20c0ec398ceab9597d104513b90336e5f4c672cbde5a3b2ece936c8a3f5148 pytorch_model-00064-of-00243.bin
|
| 69 |
+
6869b1ed0d6a2daf25939ac8ff1c696589fd62e47c114516e5726369c8e562b2 pytorch_model-00065-of-00243.bin
|
| 70 |
+
29f5ead347af64a517cb43c02140b8cca9e56831c6997709ceb92209585c9426 pytorch_model-00066-of-00243.bin
|
| 71 |
+
f3521ab2911ac86f3a8d791bd700a4cb70425f53f2639ce5d166dbf380968112 pytorch_model-00067-of-00243.bin
|
| 72 |
+
3e25fb6e55e1a627fa1bcb76c5371b8ce9b0bd233fd408a70fbc00dbb8d727c0 pytorch_model-00068-of-00243.bin
|
| 73 |
+
3e9c59b9ea19e75fe7de7ada5e41dc8c38bc95b0925eb1f41cd493d024ae6899 pytorch_model-00069-of-00243.bin
|
| 74 |
+
0aceb706fe626a8f26a52535ba9f164735aa2b9018d6f71266f07f5102bde48f pytorch_model-00070-of-00243.bin
|
| 75 |
+
43a5999497f7aee7be2f3943fb259bb283a457bbab83d08833bbc4ca55ea44d9 pytorch_model-00071-of-00243.bin
|
| 76 |
+
341304b4d0a6d8d616b6527e9a27940ff6fdff744e9d5d33648222fd788245fa pytorch_model-00072-of-00243.bin
|
| 77 |
+
ebf99e3cc61828079936a9c5b6ece50d6ca76b34f5b8e7b5544eb95771068198 pytorch_model-00073-of-00243.bin
|
| 78 |
+
afa4171a1f12702ae7ff0cdc59cae74d3211c2110a1fb4cedc9b67d5915e4519 pytorch_model-00074-of-00243.bin
|
| 79 |
+
a6980b5aa243a7c2cbd55ae561221272c32c3670f34964933f004934939eed5e pytorch_model-00075-of-00243.bin
|
| 80 |
+
c61bdce8f9252a08ecc3b4af42ee699b943ff7fe7086ca5f5c8e363ebda18d08 pytorch_model-00076-of-00243.bin
|
| 81 |
+
82139e62b584a952ef1610e251f78c9f6175d70891b7ef3240c89ca3175df5b7 pytorch_model-00077-of-00243.bin
|
| 82 |
+
0f8e26f8d0eb89d64609fe3846c3fc2b904704ce82b7b67037e4f105ea4b00e1 pytorch_model-00078-of-00243.bin
|
| 83 |
+
43a4343a8010a2e773b82a054a4b37669690a4b361d6a29eee62aa184279a22c pytorch_model-00079-of-00243.bin
|
| 84 |
+
85fc194be080bc29eace87a662f14afea9376a10b936daa89bdbc03162bfca89 pytorch_model-00080-of-00243.bin
|
| 85 |
+
016d9d5873f09d06760dabce4acb167a7115d2487fdb09a19dd0f51e195c755c pytorch_model-00081-of-00243.bin
|
| 86 |
+
fa4b253a4d70d0b6e9619fe1ca4194a64c6cdb1cc6e30e79b47a6d84068bdf52 pytorch_model-00082-of-00243.bin
|
| 87 |
+
f401abb6ebbeeaeee501f58ef182a2f0df87303e0eb3e1ef61891a564f4fe4af pytorch_model-00083-of-00243.bin
|
| 88 |
+
5565664a2f03217978813660e9ca63925e5abae9beef71b2d10772f436cdcb4e pytorch_model-00084-of-00243.bin
|
| 89 |
+
70bd36a3f6a7f45aae6e9b4b56c5889701533915d10a6b8020c93cb3ed13fb36 pytorch_model-00085-of-00243.bin
|
| 90 |
+
f0d8592e9dbadd34d090b9c309d8d2781695ecf4e6d7005addd25b13630dd611 pytorch_model-00086-of-00243.bin
|
| 91 |
+
533d20debbd4f0429f12f99ea5ce6a5b88e286af7c58604555ee7bef6c38b286 pytorch_model-00087-of-00243.bin
|
| 92 |
+
511177391ac994c00b1e39c424f8843f794c0348a9b56418c7c1584bc30d29f4 pytorch_model-00088-of-00243.bin
|
| 93 |
+
4f4c446298218fd821f5b5b9796b46650badf697fd81fa9d5af3cfa017ea2ede pytorch_model-00089-of-00243.bin
|
| 94 |
+
69935ce1a0ae99cafd3318adb16cd46005c691214d66b9c1ba2654f04bb6ee48 pytorch_model-00090-of-00243.bin
|
| 95 |
+
f8f6e703981fe6c81d09909ca4730cd50855563fc9c67804923791a19f53fe13 pytorch_model-00091-of-00243.bin
|
| 96 |
+
f4f6c8d6d43d0758840be87cf81ca1936a6ec5e7db567d7e6e28be1482ea3990 pytorch_model-00092-of-00243.bin
|
| 97 |
+
e2f13f781f5bc19ff0774b0d7d37af9ae162c372ec7b57cc6f01768349206f74 pytorch_model-00093-of-00243.bin
|
| 98 |
+
b640b907f0977649c55b5f620cefaeae0e2ab3ffa9d34004a3eaee5e5ad163e3 pytorch_model-00094-of-00243.bin
|
| 99 |
+
7028c4e1472979988f960b51b7a8872720c12e4ae77bdfc5ed2992448a497419 pytorch_model-00095-of-00243.bin
|
| 100 |
+
6c2c69a678f85a987e12eca058b60d9712f0c134fe9daf9ba45de5f8ecbf905a pytorch_model-00096-of-00243.bin
|
| 101 |
+
30747c23a557c14dca4766adedd1555529d1409045f8e8af5d8ba2912b500356 pytorch_model-00097-of-00243.bin
|
| 102 |
+
97e97a502d9354ecbc2731f93bec4b1d766636fc7b89f2be9749db719ac07400 pytorch_model-00098-of-00243.bin
|
| 103 |
+
0b7f79b28aeaddb8edcedf9ed249720c05977f13a0f7c27fe410403c0412fc0a pytorch_model-00099-of-00243.bin
|
| 104 |
+
08ebae4bfebe60c18b235bc0f6e4ee6b1659df839f1c9ddbcfad5e1398d2e923 pytorch_model-00100-of-00243.bin
|
| 105 |
+
8c8adb82ce7bef686b2cf6b64a207750249d9f725bed0b6b78249cbdd8911e48 pytorch_model-00101-of-00243.bin
|
| 106 |
+
ba24db819cf91d0f2ebc5b1ac07208cbaa71893e1cb6d8f7e0e7543173535946 pytorch_model-00102-of-00243.bin
|
| 107 |
+
74af29ea6dc24e0a1936ea080f3b70582912e0450c767a30c5360e3c62f143b9 pytorch_model-00103-of-00243.bin
|
| 108 |
+
fe068509fbae8dcfaffd178f8b830a7b3c3ddc839afff0974db4c62a701ff332 pytorch_model-00104-of-00243.bin
|
| 109 |
+
ce9f24ae56b070092e99cc119a5900b1195ad20f6a9a459a3781775f66d2266d pytorch_model-00105-of-00243.bin
|
| 110 |
+
77e7ae120c4c15a43394dcc82bdcba5fe75c844c39144d6917904111bc7cef6b pytorch_model-00106-of-00243.bin
|
| 111 |
+
dd149a6139ec2067097aebf058b4fd9b7030a49dddb8a66e323fc91000196bd6 pytorch_model-00107-of-00243.bin
|
| 112 |
+
15bc0b43afa0c818e80835fbf1e8c4213f63c0eeed1f91ed2a0c66bf9e142470 pytorch_model-00108-of-00243.bin
|
| 113 |
+
09e753f0642a1c904ef732b342894f3bd4d3f68f46989495c477eced1debde94 pytorch_model-00109-of-00243.bin
|
| 114 |
+
f3cf460b6c86e2a35fd60e3715cf9756f54c3db4bb4abc2f07c08b79002b4e19 pytorch_model-00110-of-00243.bin
|
| 115 |
+
0a353b27752a908fdc4374d041cbb5a6c912a771698d87b0f3c17874b8e488c1 pytorch_model-00111-of-00243.bin
|
| 116 |
+
63778cc7a8bc989390fd94d668c436b7ad69c86ff2f69d22f73a40bd965d3e1c pytorch_model-00112-of-00243.bin
|
| 117 |
+
11bc10f9e50374ecd18dec38dc6d0e666fb7548249bb2ec5ed67ff01778c2170 pytorch_model-00113-of-00243.bin
|
| 118 |
+
ca5885767c24be36b32cea538f90d53e05f8450224b0bb788aadd5a6dd89bd34 pytorch_model-00114-of-00243.bin
|
| 119 |
+
961620e8c9efb910851816c1dd259cb4030f529597ebc830ce539597a384b623 pytorch_model-00115-of-00243.bin
|
| 120 |
+
51ee0ac8161ccc17facabf1958ed412db37f8f5b0a190f28fe5aa16a23ade55d pytorch_model-00116-of-00243.bin
|
| 121 |
+
ad0f45f599f266e34bfaa8639b1d531744a2d841305805474c45729f0d9b777e pytorch_model-00117-of-00243.bin
|
| 122 |
+
58ac3d11f22bf981e59e856c6d78c505b0edff247e88323039a697d8d4ad57a4 pytorch_model-00118-of-00243.bin
|
| 123 |
+
1f5ab60a4639fe55130a4e8c2909c7b2e1411d8f2cbd2b00ec8341f5c9a98f06 pytorch_model-00119-of-00243.bin
|
| 124 |
+
94b4074f17ba08cfe46399d073badc2457d7ca0e3583ab690074de03ccbb62aa pytorch_model-00120-of-00243.bin
|
| 125 |
+
0a48a967e3edb8b500eaa12947a32f32f26a24b67e60d3d402afd7481df81516 pytorch_model-00121-of-00243.bin
|
| 126 |
+
fd9eb815daa468dd8be675c7248f2ff4542bbc53984562280181a01ab5a62708 pytorch_model-00122-of-00243.bin
|
| 127 |
+
fffe12cc8e0346cfc8a8230359b8ba7927294408e132218731971d90d5737b41 pytorch_model-00123-of-00243.bin
|
| 128 |
+
987380de8f157fb20e2e80aba57a8e27716e3729a736decc3758cd0d4dc73e21 pytorch_model-00124-of-00243.bin
|
| 129 |
+
6ba2b9b8a71af19c38436d7340a58fff7978575fef2deb9f89b0adb9163b2977 pytorch_model-00125-of-00243.bin
|
| 130 |
+
232f12b40cb60e6c2fb6e55bcba8a855286c16de51d1c7b0fe8c483678c04ff3 pytorch_model-00126-of-00243.bin
|
| 131 |
+
c57a3f4efb3da5660563061253fa71662e6d93e17934588eb3303691a2cb3bf3 pytorch_model-00127-of-00243.bin
|
| 132 |
+
76b14de090b4bef2c78b6ea383f18f7b6ff5dbd9dccecc55fbdfc90d71d719f3 pytorch_model-00128-of-00243.bin
|
| 133 |
+
02ff1662e0386bb56929643ff59ef8f5434277e65c5ed78fe6c78cfa68c561b0 pytorch_model-00129-of-00243.bin
|
| 134 |
+
a3e78ee0aa271f0f79b956344faca8e4f161383eb557bd1e8a5c48f26f13c5e6 pytorch_model-00130-of-00243.bin
|
| 135 |
+
01f54fd5816fc61838ec064b5cafc4c25eaa3b87937ede268b8785c426ccdd7d pytorch_model-00131-of-00243.bin
|
| 136 |
+
4ecaab016076677b83190110e275271ec4a53b3d736d945170bb1376098701ff pytorch_model-00132-of-00243.bin
|
| 137 |
+
73d18ed728d97ace5cdd89d9d0c2c76e359ceed3ad05fa03f3038b35d481db27 pytorch_model-00133-of-00243.bin
|
| 138 |
+
8b8de0770ce14282f96b36f09868aa1b8f1396f2ea2cc683e81d9b7dbdce3799 pytorch_model-00134-of-00243.bin
|
| 139 |
+
0c2e0f85e72a5e3ae5194a91edfcd141b9ebeb8654cc28769b29e79faaa7f7fe pytorch_model-00135-of-00243.bin
|
| 140 |
+
33e2206373661164a1c13008c67e2cdce7967368ebd0b2f20377ccda74723656 pytorch_model-00136-of-00243.bin
|
| 141 |
+
48d5ab98d950b69cb2807c93f97029b2019011cd7bbbc08c9f08d3390ef6f205 pytorch_model-00137-of-00243.bin
|
| 142 |
+
6435c742d6fdcbbd382d3905e46406d5af16d63d48d323301828ef8a26210fc3 pytorch_model-00138-of-00243.bin
|
| 143 |
+
c4c2593e0dcf66f315079300056c2a3f4b89c0909274bbc520e5f23cb34ad7a3 pytorch_model-00139-of-00243.bin
|
| 144 |
+
da00a68a0900c492dece277a26a9e12fae77bb1edfe32603f12c9be5ca85217a pytorch_model-00140-of-00243.bin
|
| 145 |
+
35d379ec3521bdfdb1789ad36ea80173053fcc3728c608be8760cea5805a2be2 pytorch_model-00141-of-00243.bin
|
| 146 |
+
4aba717fa9caa634aee268a2bfef4efc615a363545c23dbb997d12388b12a82d pytorch_model-00142-of-00243.bin
|
| 147 |
+
b51a06c89c8a475845c018beb6520db6ffb4a717b2bb5cb376f4e912dde124c1 pytorch_model-00143-of-00243.bin
|
| 148 |
+
ea46a5b3336bc4eb812bc1bafe1f40371585b40f5632113ca396b1064c38dd30 pytorch_model-00144-of-00243.bin
|
| 149 |
+
b346ac3f89c61c6083439c3757cedec730b672c18a35c679e08547ab873f4ecb pytorch_model-00145-of-00243.bin
|
| 150 |
+
cdf36f5445079764746a016d559d4700352e6a4e4d252d19b9d3e4b9f3552b14 pytorch_model-00146-of-00243.bin
|
| 151 |
+
6ab71611a456425ec1dee8a49f31621edb18701d876531c63ec7f19032ebaab9 pytorch_model-00147-of-00243.bin
|
| 152 |
+
530f68272df243bb3970dad56606c4f657706dfece505a7f97c4987d94c8691c pytorch_model-00148-of-00243.bin
|
| 153 |
+
3b9671d920c9506367ff83f6aa8e20c9cc3bfc955d6235e8291f200144ce1d2e pytorch_model-00149-of-00243.bin
|
| 154 |
+
cb244fe146c2e37c1a69cb2b30bf11da20082b3cad8b195e000f224764425b9a pytorch_model-00150-of-00243.bin
|
| 155 |
+
4f0bbcaabbc664e59d3a96572d0d746c2c5017c089d80ab1d6cb66047f86313e pytorch_model-00151-of-00243.bin
|
| 156 |
+
0f07bf8e97696a087a4e03db68a497ee7f8e44b8fe285717372b80e966ef6908 pytorch_model-00152-of-00243.bin
|
| 157 |
+
66ab23c030464f4b6885d54eee5189819f0399b7ce1d65cba2872f945c444c0b pytorch_model-00153-of-00243.bin
|
| 158 |
+
d10391a3fce4e7ef21a5fd041f3553b9b2b5e35c273dae79915bbec065fef613 pytorch_model-00154-of-00243.bin
|
| 159 |
+
30484b1ffc896bfa63bcd3525931821e7b984e3ceaae3a42c64d13ff92349a4e pytorch_model-00155-of-00243.bin
|
| 160 |
+
b3fd3b87151dfe5ab73598e6e48ae3331c6108e1ebbad5eecade29a6bbb314fc pytorch_model-00156-of-00243.bin
|
| 161 |
+
6a03cf30b4a4ad61a6385c6d9a169643edbfaa949459684c61f446ae361239f3 pytorch_model-00157-of-00243.bin
|
| 162 |
+
311fa925f07530e5cebcde5059bdb845db52b7f8da00623f48dc7da705a6a2df pytorch_model-00158-of-00243.bin
|
| 163 |
+
77545e68e432bacfb0bec0bc9476ad3375cfc1827da8efa9b353f9fbc758a8b8 pytorch_model-00159-of-00243.bin
|
| 164 |
+
74adb9c4554adc71b6eedc3b5a8b141b3613c1177ef0adb5bfaeeaa42bbd85a9 pytorch_model-00160-of-00243.bin
|
| 165 |
+
01b5812179799a61884ee85985ef8d8ecd00037eda2fad672dfdc2878b18a46d pytorch_model-00161-of-00243.bin
|
| 166 |
+
9650fadc97c002bbcdec1154bdd422fe12d18c61b9441ed74a1b68f545c2788b pytorch_model-00162-of-00243.bin
|
| 167 |
+
788094824dd1823f531e8cec250979556a72d22ba9d1182dbfcd3db429214b89 pytorch_model-00163-of-00243.bin
|
| 168 |
+
d755e0f69d15678a2b361212ab3d1780bf975da6d33360a5d3ed96389a02f039 pytorch_model-00164-of-00243.bin
|
| 169 |
+
5694a4c2b11ed581cdaea73cef531c26c987eedd59c221be052e8f3e443e8cfe pytorch_model-00165-of-00243.bin
|
| 170 |
+
6b0ca82e0a531a4a8f03b9ed6c5fa0c850ec1b3fd5d5f54a2c85f0e553355326 pytorch_model-00166-of-00243.bin
|
| 171 |
+
bb9afe8715554aa01b606a0b23f231b25c2762c99a2e59ca503d0e1d8b4f6a8a pytorch_model-00167-of-00243.bin
|
| 172 |
+
1c131a096d7d7363f475e6367480f5665c87111b6c58ba925474ce2ffc123799 pytorch_model-00168-of-00243.bin
|
| 173 |
+
eeaf8e409e220b251a5d9e3fac2735c13668e5da016d7c317677d4f74fe12b00 pytorch_model-00169-of-00243.bin
|
| 174 |
+
08c43e5cc128bfbbf6dd8f30e6d5bcc616c2054f341062e562927acb99922bf1 pytorch_model-00170-of-00243.bin
|
| 175 |
+
8f5b277bca1c0e05c0bd7601f4d3301d6856ff4fde62daa17a81707f60928ec5 pytorch_model-00171-of-00243.bin
|
| 176 |
+
30999caa7ced67cad5a441e3719f4ae4435a2c5591e17b08c0c2f07a18c5df5d pytorch_model-00172-of-00243.bin
|
| 177 |
+
dab1edecb2176f68468d683afe638b840f970120f9610a831c4bb5966b2f491a pytorch_model-00173-of-00243.bin
|
| 178 |
+
c82cee7ac9ecd9f6f071c244f4cf6e6e8459f8d4bb22fa38c00087195add4e6c pytorch_model-00174-of-00243.bin
|
| 179 |
+
37213a8bb345cd94e10963669f683a8c1a2378b6ff8374d863f2a09b2b0e05a1 pytorch_model-00175-of-00243.bin
|
| 180 |
+
7e80625d461a8818933861646a94e7a0d29c9ce532debea258caafb10dc4c09f pytorch_model-00176-of-00243.bin
|
| 181 |
+
4cd85828447cce382ec197771c5a4417adb37262c49c60c4440262e3c3fb45dc pytorch_model-00177-of-00243.bin
|
| 182 |
+
8c3622803909e984166c781aca5033d9fc751b76873552cdc21ec6101a371fca pytorch_model-00178-of-00243.bin
|
| 183 |
+
f7c185f4628d8ec71522b8ba2d2478d4d65d8a1de2b0f0854974929594a0cf23 pytorch_model-00179-of-00243.bin
|
| 184 |
+
a6269af0e3be281ad0b2e77fc064eadf56ff0ea50f2a1297ad93db9a76b202af pytorch_model-00180-of-00243.bin
|
| 185 |
+
b1a21ae3f3d8883734b3e8ec37eac5cc79c16a13c96e8ab945548356d0d3e447 pytorch_model-00181-of-00243.bin
|
| 186 |
+
65dfebebecac857d45e49f881b44fe52f38283da648c67b68cf8f34aaa9d7388 pytorch_model-00182-of-00243.bin
|
| 187 |
+
24dfe8116221ae9cb90ab393471d34d30f84daff0ca1632c3fc705d6c8355ba0 pytorch_model-00183-of-00243.bin
|
| 188 |
+
a02d1a5570ec7831e5c56a4e8fa9813d98415dd406f4c2fd48a3c885bdb3187b pytorch_model-00184-of-00243.bin
|
| 189 |
+
03340f30578794690dc58b97d17879f04219034f5466c4a45e3951f857c79fa1 pytorch_model-00185-of-00243.bin
|
| 190 |
+
7f5bfcc28404d85f0dffcc3ef0b014585307ade9010a004b509772b8266ec74f pytorch_model-00186-of-00243.bin
|
| 191 |
+
b3844cf4044bb1ffb02d8e9b7b1b7fd4b4c124b010c04c1f8ff8a78e03ff320f pytorch_model-00187-of-00243.bin
|
| 192 |
+
4089b0dbd91b0f2b10e7dd5fcbca4dde9faffafd661695c2da5beee8370072a3 pytorch_model-00188-of-00243.bin
|
| 193 |
+
1666768c16bfc76a11fedc3525358b9e429ae50c115b4f706960d65910715543 pytorch_model-00189-of-00243.bin
|
| 194 |
+
1affffa5fccbcc2166f666eeed7aced8d38743574ea7b6201fcd149272bb6246 pytorch_model-00190-of-00243.bin
|
| 195 |
+
ad41ac209d56068a6078429b6b18135176a9ca4ec4c24568094e1eb9ebce0f60 pytorch_model-00191-of-00243.bin
|
| 196 |
+
7ca1cab9541d33f8cbb692b5f319698c44205da210e3cdc673c9c0a2b7104b43 pytorch_model-00192-of-00243.bin
|
| 197 |
+
46d2a9a508115d14c4b4f9580a99f2b83b24222b6da6836d293f35885b610875 pytorch_model-00193-of-00243.bin
|
| 198 |
+
174844ba09a4a7471bba31188e01397be6c40e050ea685eaaa6bae22f2bb11c4 pytorch_model-00194-of-00243.bin
|
| 199 |
+
00f948d55679a438369d81791520688569c94a1b3621cb10d4454638fbcbe4db pytorch_model-00195-of-00243.bin
|
| 200 |
+
2faff3cfe1c5d530d6665a4063be2f7d26e05f0c6904cbbd7d091905d973ff79 pytorch_model-00196-of-00243.bin
|
| 201 |
+
895b6d403638393612d7d0f5cb963c80631c153f03c3d4966869057630c6f94e pytorch_model-00197-of-00243.bin
|
| 202 |
+
7dc6f3b6c479c1e775a810637d02051c8e448a8c4f6a9cd26788242dc6e515ac pytorch_model-00198-of-00243.bin
|
| 203 |
+
e0700fd25fe1be375cf7df82194120c17a154ad5c57ebfb9975f42db0aef5f48 pytorch_model-00199-of-00243.bin
|
| 204 |
+
43ea69f26fa3fc99f36a789e84022ff32a61ba3be9dac4b92e007b7361d843ca pytorch_model-00200-of-00243.bin
|
| 205 |
+
f97ffd772f8a328990d30289216d6028e6f544790af0cb81afd60205484b1c46 pytorch_model-00201-of-00243.bin
|
| 206 |
+
e1591dea37d51f02161ec7296a0787cac06d73decf4709a2ec02363ed937ddd9 pytorch_model-00202-of-00243.bin
|
| 207 |
+
ca9e94ee2efbcc51fe478068340599fca381ec4eaa40892e095ace61509e5bde pytorch_model-00203-of-00243.bin
|
| 208 |
+
37564c62aa89a31a666c3ee10dfb69bb88d6b07c2a99c0b8c16cd56913d0faf4 pytorch_model-00204-of-00243.bin
|
| 209 |
+
214824198bc777c3b026b7a164678aa7ed34a597db6fd033edaa94358395f8ae pytorch_model-00205-of-00243.bin
|
| 210 |
+
cee45752533144a37844d8eda345b613dae3f94d9da2f98f768dc3065f157a87 pytorch_model-00206-of-00243.bin
|
| 211 |
+
c9721ed5865c998b36f622f5a2c5b135fb7cd5d5e989f0ad8b6d2e9a36bce3b5 pytorch_model-00207-of-00243.bin
|
| 212 |
+
fd1323c856b7c584a0877890cd80cbddd449f4071a1180de51ac7441df33cfaf pytorch_model-00208-of-00243.bin
|
| 213 |
+
b67108c6c45e1c0426a2e890f6e15f63e5fbc9dc03b033f613b42bf7d86279ff pytorch_model-00209-of-00243.bin
|
| 214 |
+
9a3486126b67295c5533a653e354ff25b5324b8339f9d815f7ebfbca791f2378 pytorch_model-00210-of-00243.bin
|
| 215 |
+
5b624bbf42939baf3ba4d7ba25672ae363e7932d8df18b411321ea9dbab3d6c4 pytorch_model-00211-of-00243.bin
|
| 216 |
+
5005a92e9e6ccac697122bc5b8b9a0a21b4ca55e97fbe4018cfdc5fb5e869a06 pytorch_model-00212-of-00243.bin
|
| 217 |
+
ff9154478a5fd9a3b2cf5266a302497da01a538b28fbb62181d45c92d2c6c2ae pytorch_model-00213-of-00243.bin
|
| 218 |
+
4659295ce30f7ddb2c9673cf7d86280fa74869b1a08352f38406c1fbe56f51f5 pytorch_model-00214-of-00243.bin
|
| 219 |
+
794d1149608c2bb5b0007749e2474fdf7e61c150693310a1918163dbd4babfad pytorch_model-00215-of-00243.bin
|
| 220 |
+
8132b955c65d85dd5d15662ec17484143f683b78ca0af405a24725fd9393baeb pytorch_model-00216-of-00243.bin
|
| 221 |
+
640c7e2e8dca0350525ab5a51870f309b9b0203e72884be1034ef2ce74481e6e pytorch_model-00217-of-00243.bin
|
| 222 |
+
e7007217a8100f86b12894c49bac1106af5e565b03e1741b277dd02a64374fb0 pytorch_model-00218-of-00243.bin
|
| 223 |
+
c62bd6c10e27bf8d8caf92f3f13b26d92487f66a3e62f4af9e49c7eba63167b8 pytorch_model-00219-of-00243.bin
|
| 224 |
+
1e657f439b4a2db41cdaeadcdb88f5eb48a8cd726ac460da9cdefd0502b3eb9b pytorch_model-00220-of-00243.bin
|
| 225 |
+
de028b5f2a19b85c5be2d0654ae2337516220ec27669ffc8ef17c43104bb3224 pytorch_model-00221-of-00243.bin
|
| 226 |
+
3ad8fc90c1fb9bb43cfe5b2401bfb7b290ce8c704bbc5515f1ce4a5873f95139 pytorch_model-00222-of-00243.bin
|
| 227 |
+
9b989a86fa6dcf0436cc974981f6d3c8811132e92a26166a25ea457c72b3db06 pytorch_model-00223-of-00243.bin
|
| 228 |
+
aca6597466a65388286be22891e5474fd1e79eda6b2b1b3f968163a7b1a4393d pytorch_model-00224-of-00243.bin
|
| 229 |
+
fd0f867516832221d24705969d3593e5a1811ee761b8fbf7c57bcc1ad1dfc8a5 pytorch_model-00225-of-00243.bin
|
| 230 |
+
6794576954ec8970ff09499a7c0de486532326826f850bbdbf2e3fa815f69e1e pytorch_model-00226-of-00243.bin
|
| 231 |
+
4f7cef542e67021df4ff812429ea0491ef967122d94afa3cdd83b41181fa3c75 pytorch_model-00227-of-00243.bin
|
| 232 |
+
fee6c54c08d1efabc58eaa318651a625199cea878e49dd9257ec8d493009a779 pytorch_model-00228-of-00243.bin
|
| 233 |
+
ae514ec50b760014c719a16b9509b5cb3b0d9f82dfd4d489cc3d3484e8d6a9a7 pytorch_model-00229-of-00243.bin
|
| 234 |
+
6d4b7fb5ec49a09cafc0977126e0d22a7acd1f029dff96efe130c665373619f6 pytorch_model-00230-of-00243.bin
|
| 235 |
+
fcfa6ba6f24e9ae498769fd4a3e20c2f183ea290640de2f205a378d50c44c457 pytorch_model-00231-of-00243.bin
|
| 236 |
+
9f1994823e8a45ccdd4030a3abbbed28026a08fa5908ccacf7cb0f9976ad8976 pytorch_model-00232-of-00243.bin
|
| 237 |
+
cf64ed719e75ab225838749b8885e00c23b280a1c750b9f695aac00ad89152aa pytorch_model-00233-of-00243.bin
|
| 238 |
+
befc340950c3750e9fb79be5f7a3ba7ecb5bcc5422bd327e9309fb440dbbb5be pytorch_model-00234-of-00243.bin
|
| 239 |
+
abc57ae3f55a7ee8fb3fac3e36531b1e577fb4916a6b1c3fa88d7ce9969aed5f pytorch_model-00235-of-00243.bin
|
| 240 |
+
29bb9ec1e0db7a8d1dba82cfc430a6d8a6f1620dd0006a36de3a8f90cb943bac pytorch_model-00236-of-00243.bin
|
| 241 |
+
14d20d28ee07dbaba393a8d82aa17683bc31d988fb4f22d261336dd5096ae71c pytorch_model-00237-of-00243.bin
|
| 242 |
+
58df1115168fe8d60dffd81f7e0a2d5b0997601ca73f75cfab9ba128a3a3d496 pytorch_model-00238-of-00243.bin
|
| 243 |
+
7f42e2a869414c1cba14c3bb0b3e72fabc06a8a77144dac233c366c1883073b8 pytorch_model-00239-of-00243.bin
|
| 244 |
+
a4faa71e384023a2e1e21609bf5b6967925df8f2b64d825183fad2fb2418985a pytorch_model-00240-of-00243.bin
|
| 245 |
+
530296bfc60095c9f4840776a6ee24558efddcf19bd1a7ebe42895c02d7e912c pytorch_model-00241-of-00243.bin
|
| 246 |
+
8bc75fb2c6486f123c89701022ed29145c1246fe109a3defa5d470b35074a988 pytorch_model-00242-of-00243.bin
|
| 247 |
+
39f587e500e18a9db4797a87945ef84b9dc7bb989506f7d322144b270918358c pytorch_model-00243-of-00243.bin
|
| 248 |
+
9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347 tokenizer.model
|
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-00243-of-00243.bin",
|
| 7 |
+
"model.embed_tokens.weight": "pytorch_model-00002-of-00243.bin",
|
| 8 |
+
"model.layers.0.input_layernorm.weight": "pytorch_model-00006-of-00243.bin",
|
| 9 |
+
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00005-of-00243.bin",
|
| 10 |
+
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00004-of-00243.bin",
|
| 11 |
+
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00006-of-00243.bin",
|
| 12 |
+
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00006-of-00243.bin",
|
| 13 |
+
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00003-of-00243.bin",
|
| 14 |
+
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00003-of-00243.bin",
|
| 15 |
+
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00003-of-00243.bin",
|
| 16 |
+
"model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00243.bin",
|
| 17 |
+
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00003-of-00243.bin",
|
| 18 |
+
"model.layers.1.input_layernorm.weight": "pytorch_model-00010-of-00243.bin",
|
| 19 |
+
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00009-of-00243.bin",
|
| 20 |
+
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00008-of-00243.bin",
|
| 21 |
+
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00010-of-00243.bin",
|
| 22 |
+
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00010-of-00243.bin",
|
| 23 |
+
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00007-of-00243.bin",
|
| 24 |
+
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00007-of-00243.bin",
|
| 25 |
+
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00006-of-00243.bin",
|
| 26 |
+
"model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00243.bin",
|
| 27 |
+
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00007-of-00243.bin",
|
| 28 |
+
"model.layers.10.input_layernorm.weight": "pytorch_model-00046-of-00243.bin",
|
| 29 |
+
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00045-of-00243.bin",
|
| 30 |
+
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00044-of-00243.bin",
|
| 31 |
+
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00046-of-00243.bin",
|
| 32 |
+
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00046-of-00243.bin",
|
| 33 |
+
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00043-of-00243.bin",
|
| 34 |
+
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00043-of-00243.bin",
|
| 35 |
+
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00042-of-00243.bin",
|
| 36 |
+
"model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00043-of-00243.bin",
|
| 37 |
+
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00043-of-00243.bin",
|
| 38 |
+
"model.layers.11.input_layernorm.weight": "pytorch_model-00050-of-00243.bin",
|
| 39 |
+
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00049-of-00243.bin",
|
| 40 |
+
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00048-of-00243.bin",
|
| 41 |
+
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00050-of-00243.bin",
|
| 42 |
+
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00050-of-00243.bin",
|
| 43 |
+
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00047-of-00243.bin",
|
| 44 |
+
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00047-of-00243.bin",
|
| 45 |
+
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00046-of-00243.bin",
|
| 46 |
+
"model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00047-of-00243.bin",
|
| 47 |
+
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00047-of-00243.bin",
|
| 48 |
+
"model.layers.12.input_layernorm.weight": "pytorch_model-00054-of-00243.bin",
|
| 49 |
+
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00053-of-00243.bin",
|
| 50 |
+
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00052-of-00243.bin",
|
| 51 |
+
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00054-of-00243.bin",
|
| 52 |
+
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00054-of-00243.bin",
|
| 53 |
+
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00051-of-00243.bin",
|
| 54 |
+
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00051-of-00243.bin",
|
| 55 |
+
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00050-of-00243.bin",
|
| 56 |
+
"model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00051-of-00243.bin",
|
| 57 |
+
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00051-of-00243.bin",
|
| 58 |
+
"model.layers.13.input_layernorm.weight": "pytorch_model-00058-of-00243.bin",
|
| 59 |
+
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00057-of-00243.bin",
|
| 60 |
+
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00056-of-00243.bin",
|
| 61 |
+
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00058-of-00243.bin",
|
| 62 |
+
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00058-of-00243.bin",
|
| 63 |
+
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00055-of-00243.bin",
|
| 64 |
+
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00055-of-00243.bin",
|
| 65 |
+
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00054-of-00243.bin",
|
| 66 |
+
"model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00055-of-00243.bin",
|
| 67 |
+
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00055-of-00243.bin",
|
| 68 |
+
"model.layers.14.input_layernorm.weight": "pytorch_model-00062-of-00243.bin",
|
| 69 |
+
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00061-of-00243.bin",
|
| 70 |
+
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00060-of-00243.bin",
|
| 71 |
+
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00062-of-00243.bin",
|
| 72 |
+
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00062-of-00243.bin",
|
| 73 |
+
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00059-of-00243.bin",
|
| 74 |
+
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00059-of-00243.bin",
|
| 75 |
+
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00058-of-00243.bin",
|
| 76 |
+
"model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00059-of-00243.bin",
|
| 77 |
+
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00059-of-00243.bin",
|
| 78 |
+
"model.layers.15.input_layernorm.weight": "pytorch_model-00066-of-00243.bin",
|
| 79 |
+
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00065-of-00243.bin",
|
| 80 |
+
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00064-of-00243.bin",
|
| 81 |
+
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00066-of-00243.bin",
|
| 82 |
+
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00066-of-00243.bin",
|
| 83 |
+
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00063-of-00243.bin",
|
| 84 |
+
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00063-of-00243.bin",
|
| 85 |
+
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00062-of-00243.bin",
|
| 86 |
+
"model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00063-of-00243.bin",
|
| 87 |
+
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00063-of-00243.bin",
|
| 88 |
+
"model.layers.16.input_layernorm.weight": "pytorch_model-00070-of-00243.bin",
|
| 89 |
+
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00069-of-00243.bin",
|
| 90 |
+
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00068-of-00243.bin",
|
| 91 |
+
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00070-of-00243.bin",
|
| 92 |
+
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00070-of-00243.bin",
|
| 93 |
+
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00067-of-00243.bin",
|
| 94 |
+
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00067-of-00243.bin",
|
| 95 |
+
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00066-of-00243.bin",
|
| 96 |
+
"model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00067-of-00243.bin",
|
| 97 |
+
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00067-of-00243.bin",
|
| 98 |
+
"model.layers.17.input_layernorm.weight": "pytorch_model-00074-of-00243.bin",
|
| 99 |
+
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00073-of-00243.bin",
|
| 100 |
+
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00072-of-00243.bin",
|
| 101 |
+
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00074-of-00243.bin",
|
| 102 |
+
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00074-of-00243.bin",
|
| 103 |
+
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00071-of-00243.bin",
|
| 104 |
+
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00071-of-00243.bin",
|
| 105 |
+
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00070-of-00243.bin",
|
| 106 |
+
"model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00071-of-00243.bin",
|
| 107 |
+
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00071-of-00243.bin",
|
| 108 |
+
"model.layers.18.input_layernorm.weight": "pytorch_model-00078-of-00243.bin",
|
| 109 |
+
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00077-of-00243.bin",
|
| 110 |
+
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00076-of-00243.bin",
|
| 111 |
+
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00078-of-00243.bin",
|
| 112 |
+
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00078-of-00243.bin",
|
| 113 |
+
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00075-of-00243.bin",
|
| 114 |
+
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00075-of-00243.bin",
|
| 115 |
+
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00074-of-00243.bin",
|
| 116 |
+
"model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00075-of-00243.bin",
|
| 117 |
+
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00075-of-00243.bin",
|
| 118 |
+
"model.layers.19.input_layernorm.weight": "pytorch_model-00082-of-00243.bin",
|
| 119 |
+
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00081-of-00243.bin",
|
| 120 |
+
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00080-of-00243.bin",
|
| 121 |
+
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00082-of-00243.bin",
|
| 122 |
+
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00082-of-00243.bin",
|
| 123 |
+
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00079-of-00243.bin",
|
| 124 |
+
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00079-of-00243.bin",
|
| 125 |
+
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00078-of-00243.bin",
|
| 126 |
+
"model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00079-of-00243.bin",
|
| 127 |
+
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00079-of-00243.bin",
|
| 128 |
+
"model.layers.2.input_layernorm.weight": "pytorch_model-00014-of-00243.bin",
|
| 129 |
+
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00013-of-00243.bin",
|
| 130 |
+
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00012-of-00243.bin",
|
| 131 |
+
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00014-of-00243.bin",
|
| 132 |
+
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00014-of-00243.bin",
|
| 133 |
+
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00011-of-00243.bin",
|
| 134 |
+
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00011-of-00243.bin",
|
| 135 |
+
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00010-of-00243.bin",
|
| 136 |
+
"model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00243.bin",
|
| 137 |
+
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00011-of-00243.bin",
|
| 138 |
+
"model.layers.20.input_layernorm.weight": "pytorch_model-00086-of-00243.bin",
|
| 139 |
+
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00085-of-00243.bin",
|
| 140 |
+
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00084-of-00243.bin",
|
| 141 |
+
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00086-of-00243.bin",
|
| 142 |
+
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00086-of-00243.bin",
|
| 143 |
+
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00083-of-00243.bin",
|
| 144 |
+
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00083-of-00243.bin",
|
| 145 |
+
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00082-of-00243.bin",
|
| 146 |
+
"model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00083-of-00243.bin",
|
| 147 |
+
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00083-of-00243.bin",
|
| 148 |
+
"model.layers.21.input_layernorm.weight": "pytorch_model-00090-of-00243.bin",
|
| 149 |
+
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00089-of-00243.bin",
|
| 150 |
+
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00088-of-00243.bin",
|
| 151 |
+
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00090-of-00243.bin",
|
| 152 |
+
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00090-of-00243.bin",
|
| 153 |
+
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00087-of-00243.bin",
|
| 154 |
+
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00087-of-00243.bin",
|
| 155 |
+
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00086-of-00243.bin",
|
| 156 |
+
"model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00087-of-00243.bin",
|
| 157 |
+
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00087-of-00243.bin",
|
| 158 |
+
"model.layers.22.input_layernorm.weight": "pytorch_model-00094-of-00243.bin",
|
| 159 |
+
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00093-of-00243.bin",
|
| 160 |
+
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00092-of-00243.bin",
|
| 161 |
+
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00094-of-00243.bin",
|
| 162 |
+
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00094-of-00243.bin",
|
| 163 |
+
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00091-of-00243.bin",
|
| 164 |
+
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00091-of-00243.bin",
|
| 165 |
+
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00090-of-00243.bin",
|
| 166 |
+
"model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00091-of-00243.bin",
|
| 167 |
+
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00091-of-00243.bin",
|
| 168 |
+
"model.layers.23.input_layernorm.weight": "pytorch_model-00098-of-00243.bin",
|
| 169 |
+
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00097-of-00243.bin",
|
| 170 |
+
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00096-of-00243.bin",
|
| 171 |
+
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00098-of-00243.bin",
|
| 172 |
+
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00098-of-00243.bin",
|
| 173 |
+
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00095-of-00243.bin",
|
| 174 |
+
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00095-of-00243.bin",
|
| 175 |
+
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00094-of-00243.bin",
|
| 176 |
+
"model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00095-of-00243.bin",
|
| 177 |
+
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00095-of-00243.bin",
|
| 178 |
+
"model.layers.24.input_layernorm.weight": "pytorch_model-00102-of-00243.bin",
|
| 179 |
+
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00101-of-00243.bin",
|
| 180 |
+
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00100-of-00243.bin",
|
| 181 |
+
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00102-of-00243.bin",
|
| 182 |
+
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00102-of-00243.bin",
|
| 183 |
+
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00099-of-00243.bin",
|
| 184 |
+
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00099-of-00243.bin",
|
| 185 |
+
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00098-of-00243.bin",
|
| 186 |
+
"model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00099-of-00243.bin",
|
| 187 |
+
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00099-of-00243.bin",
|
| 188 |
+
"model.layers.25.input_layernorm.weight": "pytorch_model-00106-of-00243.bin",
|
| 189 |
+
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00105-of-00243.bin",
|
| 190 |
+
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00104-of-00243.bin",
|
| 191 |
+
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00106-of-00243.bin",
|
| 192 |
+
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00106-of-00243.bin",
|
| 193 |
+
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00103-of-00243.bin",
|
| 194 |
+
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00103-of-00243.bin",
|
| 195 |
+
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00102-of-00243.bin",
|
| 196 |
+
"model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00103-of-00243.bin",
|
| 197 |
+
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00103-of-00243.bin",
|
| 198 |
+
"model.layers.26.input_layernorm.weight": "pytorch_model-00110-of-00243.bin",
|
| 199 |
+
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00109-of-00243.bin",
|
| 200 |
+
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00108-of-00243.bin",
|
| 201 |
+
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00110-of-00243.bin",
|
| 202 |
+
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00110-of-00243.bin",
|
| 203 |
+
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00107-of-00243.bin",
|
| 204 |
+
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00107-of-00243.bin",
|
| 205 |
+
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00106-of-00243.bin",
|
| 206 |
+
"model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00107-of-00243.bin",
|
| 207 |
+
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00107-of-00243.bin",
|
| 208 |
+
"model.layers.27.input_layernorm.weight": "pytorch_model-00114-of-00243.bin",
|
| 209 |
+
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00113-of-00243.bin",
|
| 210 |
+
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00112-of-00243.bin",
|
| 211 |
+
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00114-of-00243.bin",
|
| 212 |
+
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00114-of-00243.bin",
|
| 213 |
+
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00111-of-00243.bin",
|
| 214 |
+
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00111-of-00243.bin",
|
| 215 |
+
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00110-of-00243.bin",
|
| 216 |
+
"model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00111-of-00243.bin",
|
| 217 |
+
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00111-of-00243.bin",
|
| 218 |
+
"model.layers.28.input_layernorm.weight": "pytorch_model-00118-of-00243.bin",
|
| 219 |
+
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00117-of-00243.bin",
|
| 220 |
+
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00116-of-00243.bin",
|
| 221 |
+
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00118-of-00243.bin",
|
| 222 |
+
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00118-of-00243.bin",
|
| 223 |
+
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00115-of-00243.bin",
|
| 224 |
+
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00115-of-00243.bin",
|
| 225 |
+
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00114-of-00243.bin",
|
| 226 |
+
"model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00115-of-00243.bin",
|
| 227 |
+
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00115-of-00243.bin",
|
| 228 |
+
"model.layers.29.input_layernorm.weight": "pytorch_model-00122-of-00243.bin",
|
| 229 |
+
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00121-of-00243.bin",
|
| 230 |
+
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00120-of-00243.bin",
|
| 231 |
+
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00122-of-00243.bin",
|
| 232 |
+
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00122-of-00243.bin",
|
| 233 |
+
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00119-of-00243.bin",
|
| 234 |
+
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00119-of-00243.bin",
|
| 235 |
+
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00118-of-00243.bin",
|
| 236 |
+
"model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00119-of-00243.bin",
|
| 237 |
+
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00119-of-00243.bin",
|
| 238 |
+
"model.layers.3.input_layernorm.weight": "pytorch_model-00018-of-00243.bin",
|
| 239 |
+
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00017-of-00243.bin",
|
| 240 |
+
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00016-of-00243.bin",
|
| 241 |
+
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00018-of-00243.bin",
|
| 242 |
+
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00018-of-00243.bin",
|
| 243 |
+
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00015-of-00243.bin",
|
| 244 |
+
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00015-of-00243.bin",
|
| 245 |
+
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00014-of-00243.bin",
|
| 246 |
+
"model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00015-of-00243.bin",
|
| 247 |
+
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00015-of-00243.bin",
|
| 248 |
+
"model.layers.30.input_layernorm.weight": "pytorch_model-00126-of-00243.bin",
|
| 249 |
+
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00125-of-00243.bin",
|
| 250 |
+
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00124-of-00243.bin",
|
| 251 |
+
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00126-of-00243.bin",
|
| 252 |
+
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00126-of-00243.bin",
|
| 253 |
+
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00123-of-00243.bin",
|
| 254 |
+
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00123-of-00243.bin",
|
| 255 |
+
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00122-of-00243.bin",
|
| 256 |
+
"model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00123-of-00243.bin",
|
| 257 |
+
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00123-of-00243.bin",
|
| 258 |
+
"model.layers.31.input_layernorm.weight": "pytorch_model-00130-of-00243.bin",
|
| 259 |
+
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00129-of-00243.bin",
|
| 260 |
+
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00128-of-00243.bin",
|
| 261 |
+
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00130-of-00243.bin",
|
| 262 |
+
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00130-of-00243.bin",
|
| 263 |
+
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00127-of-00243.bin",
|
| 264 |
+
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00127-of-00243.bin",
|
| 265 |
+
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00126-of-00243.bin",
|
| 266 |
+
"model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00127-of-00243.bin",
|
| 267 |
+
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00127-of-00243.bin",
|
| 268 |
+
"model.layers.32.input_layernorm.weight": "pytorch_model-00134-of-00243.bin",
|
| 269 |
+
"model.layers.32.mlp.down_proj.weight": "pytorch_model-00133-of-00243.bin",
|
| 270 |
+
"model.layers.32.mlp.gate_proj.weight": "pytorch_model-00132-of-00243.bin",
|
| 271 |
+
"model.layers.32.mlp.up_proj.weight": "pytorch_model-00134-of-00243.bin",
|
| 272 |
+
"model.layers.32.post_attention_layernorm.weight": "pytorch_model-00134-of-00243.bin",
|
| 273 |
+
"model.layers.32.self_attn.k_proj.weight": "pytorch_model-00131-of-00243.bin",
|
| 274 |
+
"model.layers.32.self_attn.o_proj.weight": "pytorch_model-00131-of-00243.bin",
|
| 275 |
+
"model.layers.32.self_attn.q_proj.weight": "pytorch_model-00130-of-00243.bin",
|
| 276 |
+
"model.layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-00131-of-00243.bin",
|
| 277 |
+
"model.layers.32.self_attn.v_proj.weight": "pytorch_model-00131-of-00243.bin",
|
| 278 |
+
"model.layers.33.input_layernorm.weight": "pytorch_model-00138-of-00243.bin",
|
| 279 |
+
"model.layers.33.mlp.down_proj.weight": "pytorch_model-00137-of-00243.bin",
|
| 280 |
+
"model.layers.33.mlp.gate_proj.weight": "pytorch_model-00136-of-00243.bin",
|
| 281 |
+
"model.layers.33.mlp.up_proj.weight": "pytorch_model-00138-of-00243.bin",
|
| 282 |
+
"model.layers.33.post_attention_layernorm.weight": "pytorch_model-00138-of-00243.bin",
|
| 283 |
+
"model.layers.33.self_attn.k_proj.weight": "pytorch_model-00135-of-00243.bin",
|
| 284 |
+
"model.layers.33.self_attn.o_proj.weight": "pytorch_model-00135-of-00243.bin",
|
| 285 |
+
"model.layers.33.self_attn.q_proj.weight": "pytorch_model-00134-of-00243.bin",
|
| 286 |
+
"model.layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-00135-of-00243.bin",
|
| 287 |
+
"model.layers.33.self_attn.v_proj.weight": "pytorch_model-00135-of-00243.bin",
|
| 288 |
+
"model.layers.34.input_layernorm.weight": "pytorch_model-00142-of-00243.bin",
|
| 289 |
+
"model.layers.34.mlp.down_proj.weight": "pytorch_model-00141-of-00243.bin",
|
| 290 |
+
"model.layers.34.mlp.gate_proj.weight": "pytorch_model-00140-of-00243.bin",
|
| 291 |
+
"model.layers.34.mlp.up_proj.weight": "pytorch_model-00142-of-00243.bin",
|
| 292 |
+
"model.layers.34.post_attention_layernorm.weight": "pytorch_model-00142-of-00243.bin",
|
| 293 |
+
"model.layers.34.self_attn.k_proj.weight": "pytorch_model-00139-of-00243.bin",
|
| 294 |
+
"model.layers.34.self_attn.o_proj.weight": "pytorch_model-00139-of-00243.bin",
|
| 295 |
+
"model.layers.34.self_attn.q_proj.weight": "pytorch_model-00138-of-00243.bin",
|
| 296 |
+
"model.layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-00139-of-00243.bin",
|
| 297 |
+
"model.layers.34.self_attn.v_proj.weight": "pytorch_model-00139-of-00243.bin",
|
| 298 |
+
"model.layers.35.input_layernorm.weight": "pytorch_model-00146-of-00243.bin",
|
| 299 |
+
"model.layers.35.mlp.down_proj.weight": "pytorch_model-00145-of-00243.bin",
|
| 300 |
+
"model.layers.35.mlp.gate_proj.weight": "pytorch_model-00144-of-00243.bin",
|
| 301 |
+
"model.layers.35.mlp.up_proj.weight": "pytorch_model-00146-of-00243.bin",
|
| 302 |
+
"model.layers.35.post_attention_layernorm.weight": "pytorch_model-00146-of-00243.bin",
|
| 303 |
+
"model.layers.35.self_attn.k_proj.weight": "pytorch_model-00143-of-00243.bin",
|
| 304 |
+
"model.layers.35.self_attn.o_proj.weight": "pytorch_model-00143-of-00243.bin",
|
| 305 |
+
"model.layers.35.self_attn.q_proj.weight": "pytorch_model-00142-of-00243.bin",
|
| 306 |
+
"model.layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-00143-of-00243.bin",
|
| 307 |
+
"model.layers.35.self_attn.v_proj.weight": "pytorch_model-00143-of-00243.bin",
|
| 308 |
+
"model.layers.36.input_layernorm.weight": "pytorch_model-00150-of-00243.bin",
|
| 309 |
+
"model.layers.36.mlp.down_proj.weight": "pytorch_model-00149-of-00243.bin",
|
| 310 |
+
"model.layers.36.mlp.gate_proj.weight": "pytorch_model-00148-of-00243.bin",
|
| 311 |
+
"model.layers.36.mlp.up_proj.weight": "pytorch_model-00150-of-00243.bin",
|
| 312 |
+
"model.layers.36.post_attention_layernorm.weight": "pytorch_model-00150-of-00243.bin",
|
| 313 |
+
"model.layers.36.self_attn.k_proj.weight": "pytorch_model-00147-of-00243.bin",
|
| 314 |
+
"model.layers.36.self_attn.o_proj.weight": "pytorch_model-00147-of-00243.bin",
|
| 315 |
+
"model.layers.36.self_attn.q_proj.weight": "pytorch_model-00146-of-00243.bin",
|
| 316 |
+
"model.layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-00147-of-00243.bin",
|
| 317 |
+
"model.layers.36.self_attn.v_proj.weight": "pytorch_model-00147-of-00243.bin",
|
| 318 |
+
"model.layers.37.input_layernorm.weight": "pytorch_model-00154-of-00243.bin",
|
| 319 |
+
"model.layers.37.mlp.down_proj.weight": "pytorch_model-00153-of-00243.bin",
|
| 320 |
+
"model.layers.37.mlp.gate_proj.weight": "pytorch_model-00152-of-00243.bin",
|
| 321 |
+
"model.layers.37.mlp.up_proj.weight": "pytorch_model-00154-of-00243.bin",
|
| 322 |
+
"model.layers.37.post_attention_layernorm.weight": "pytorch_model-00154-of-00243.bin",
|
| 323 |
+
"model.layers.37.self_attn.k_proj.weight": "pytorch_model-00151-of-00243.bin",
|
| 324 |
+
"model.layers.37.self_attn.o_proj.weight": "pytorch_model-00151-of-00243.bin",
|
| 325 |
+
"model.layers.37.self_attn.q_proj.weight": "pytorch_model-00150-of-00243.bin",
|
| 326 |
+
"model.layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-00151-of-00243.bin",
|
| 327 |
+
"model.layers.37.self_attn.v_proj.weight": "pytorch_model-00151-of-00243.bin",
|
| 328 |
+
"model.layers.38.input_layernorm.weight": "pytorch_model-00158-of-00243.bin",
|
| 329 |
+
"model.layers.38.mlp.down_proj.weight": "pytorch_model-00157-of-00243.bin",
|
| 330 |
+
"model.layers.38.mlp.gate_proj.weight": "pytorch_model-00156-of-00243.bin",
|
| 331 |
+
"model.layers.38.mlp.up_proj.weight": "pytorch_model-00158-of-00243.bin",
|
| 332 |
+
"model.layers.38.post_attention_layernorm.weight": "pytorch_model-00158-of-00243.bin",
|
| 333 |
+
"model.layers.38.self_attn.k_proj.weight": "pytorch_model-00155-of-00243.bin",
|
| 334 |
+
"model.layers.38.self_attn.o_proj.weight": "pytorch_model-00155-of-00243.bin",
|
| 335 |
+
"model.layers.38.self_attn.q_proj.weight": "pytorch_model-00154-of-00243.bin",
|
| 336 |
+
"model.layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-00155-of-00243.bin",
|
| 337 |
+
"model.layers.38.self_attn.v_proj.weight": "pytorch_model-00155-of-00243.bin",
|
| 338 |
+
"model.layers.39.input_layernorm.weight": "pytorch_model-00162-of-00243.bin",
|
| 339 |
+
"model.layers.39.mlp.down_proj.weight": "pytorch_model-00161-of-00243.bin",
|
| 340 |
+
"model.layers.39.mlp.gate_proj.weight": "pytorch_model-00160-of-00243.bin",
|
| 341 |
+
"model.layers.39.mlp.up_proj.weight": "pytorch_model-00162-of-00243.bin",
|
| 342 |
+
"model.layers.39.post_attention_layernorm.weight": "pytorch_model-00162-of-00243.bin",
|
| 343 |
+
"model.layers.39.self_attn.k_proj.weight": "pytorch_model-00159-of-00243.bin",
|
| 344 |
+
"model.layers.39.self_attn.o_proj.weight": "pytorch_model-00159-of-00243.bin",
|
| 345 |
+
"model.layers.39.self_attn.q_proj.weight": "pytorch_model-00158-of-00243.bin",
|
| 346 |
+
"model.layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-00159-of-00243.bin",
|
| 347 |
+
"model.layers.39.self_attn.v_proj.weight": "pytorch_model-00159-of-00243.bin",
|
| 348 |
+
"model.layers.4.input_layernorm.weight": "pytorch_model-00022-of-00243.bin",
|
| 349 |
+
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00021-of-00243.bin",
|
| 350 |
+
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00020-of-00243.bin",
|
| 351 |
+
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00022-of-00243.bin",
|
| 352 |
+
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00022-of-00243.bin",
|
| 353 |
+
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00019-of-00243.bin",
|
| 354 |
+
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00019-of-00243.bin",
|
| 355 |
+
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00018-of-00243.bin",
|
| 356 |
+
"model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00019-of-00243.bin",
|
| 357 |
+
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00019-of-00243.bin",
|
| 358 |
+
"model.layers.40.input_layernorm.weight": "pytorch_model-00166-of-00243.bin",
|
| 359 |
+
"model.layers.40.mlp.down_proj.weight": "pytorch_model-00165-of-00243.bin",
|
| 360 |
+
"model.layers.40.mlp.gate_proj.weight": "pytorch_model-00164-of-00243.bin",
|
| 361 |
+
"model.layers.40.mlp.up_proj.weight": "pytorch_model-00166-of-00243.bin",
|
| 362 |
+
"model.layers.40.post_attention_layernorm.weight": "pytorch_model-00166-of-00243.bin",
|
| 363 |
+
"model.layers.40.self_attn.k_proj.weight": "pytorch_model-00163-of-00243.bin",
|
| 364 |
+
"model.layers.40.self_attn.o_proj.weight": "pytorch_model-00163-of-00243.bin",
|
| 365 |
+
"model.layers.40.self_attn.q_proj.weight": "pytorch_model-00162-of-00243.bin",
|
| 366 |
+
"model.layers.40.self_attn.rotary_emb.inv_freq": "pytorch_model-00163-of-00243.bin",
|
| 367 |
+
"model.layers.40.self_attn.v_proj.weight": "pytorch_model-00163-of-00243.bin",
|
| 368 |
+
"model.layers.41.input_layernorm.weight": "pytorch_model-00170-of-00243.bin",
|
| 369 |
+
"model.layers.41.mlp.down_proj.weight": "pytorch_model-00169-of-00243.bin",
|
| 370 |
+
"model.layers.41.mlp.gate_proj.weight": "pytorch_model-00168-of-00243.bin",
|
| 371 |
+
"model.layers.41.mlp.up_proj.weight": "pytorch_model-00170-of-00243.bin",
|
| 372 |
+
"model.layers.41.post_attention_layernorm.weight": "pytorch_model-00170-of-00243.bin",
|
| 373 |
+
"model.layers.41.self_attn.k_proj.weight": "pytorch_model-00167-of-00243.bin",
|
| 374 |
+
"model.layers.41.self_attn.o_proj.weight": "pytorch_model-00167-of-00243.bin",
|
| 375 |
+
"model.layers.41.self_attn.q_proj.weight": "pytorch_model-00166-of-00243.bin",
|
| 376 |
+
"model.layers.41.self_attn.rotary_emb.inv_freq": "pytorch_model-00167-of-00243.bin",
|
| 377 |
+
"model.layers.41.self_attn.v_proj.weight": "pytorch_model-00167-of-00243.bin",
|
| 378 |
+
"model.layers.42.input_layernorm.weight": "pytorch_model-00174-of-00243.bin",
|
| 379 |
+
"model.layers.42.mlp.down_proj.weight": "pytorch_model-00173-of-00243.bin",
|
| 380 |
+
"model.layers.42.mlp.gate_proj.weight": "pytorch_model-00172-of-00243.bin",
|
| 381 |
+
"model.layers.42.mlp.up_proj.weight": "pytorch_model-00174-of-00243.bin",
|
| 382 |
+
"model.layers.42.post_attention_layernorm.weight": "pytorch_model-00174-of-00243.bin",
|
| 383 |
+
"model.layers.42.self_attn.k_proj.weight": "pytorch_model-00171-of-00243.bin",
|
| 384 |
+
"model.layers.42.self_attn.o_proj.weight": "pytorch_model-00171-of-00243.bin",
|
| 385 |
+
"model.layers.42.self_attn.q_proj.weight": "pytorch_model-00170-of-00243.bin",
|
| 386 |
+
"model.layers.42.self_attn.rotary_emb.inv_freq": "pytorch_model-00171-of-00243.bin",
|
| 387 |
+
"model.layers.42.self_attn.v_proj.weight": "pytorch_model-00171-of-00243.bin",
|
| 388 |
+
"model.layers.43.input_layernorm.weight": "pytorch_model-00178-of-00243.bin",
|
| 389 |
+
"model.layers.43.mlp.down_proj.weight": "pytorch_model-00177-of-00243.bin",
|
| 390 |
+
"model.layers.43.mlp.gate_proj.weight": "pytorch_model-00176-of-00243.bin",
|
| 391 |
+
"model.layers.43.mlp.up_proj.weight": "pytorch_model-00178-of-00243.bin",
|
| 392 |
+
"model.layers.43.post_attention_layernorm.weight": "pytorch_model-00178-of-00243.bin",
|
| 393 |
+
"model.layers.43.self_attn.k_proj.weight": "pytorch_model-00175-of-00243.bin",
|
| 394 |
+
"model.layers.43.self_attn.o_proj.weight": "pytorch_model-00175-of-00243.bin",
|
| 395 |
+
"model.layers.43.self_attn.q_proj.weight": "pytorch_model-00174-of-00243.bin",
|
| 396 |
+
"model.layers.43.self_attn.rotary_emb.inv_freq": "pytorch_model-00175-of-00243.bin",
|
| 397 |
+
"model.layers.43.self_attn.v_proj.weight": "pytorch_model-00175-of-00243.bin",
|
| 398 |
+
"model.layers.44.input_layernorm.weight": "pytorch_model-00182-of-00243.bin",
|
| 399 |
+
"model.layers.44.mlp.down_proj.weight": "pytorch_model-00181-of-00243.bin",
|
| 400 |
+
"model.layers.44.mlp.gate_proj.weight": "pytorch_model-00180-of-00243.bin",
|
| 401 |
+
"model.layers.44.mlp.up_proj.weight": "pytorch_model-00182-of-00243.bin",
|
| 402 |
+
"model.layers.44.post_attention_layernorm.weight": "pytorch_model-00182-of-00243.bin",
|
| 403 |
+
"model.layers.44.self_attn.k_proj.weight": "pytorch_model-00179-of-00243.bin",
|
| 404 |
+
"model.layers.44.self_attn.o_proj.weight": "pytorch_model-00179-of-00243.bin",
|
| 405 |
+
"model.layers.44.self_attn.q_proj.weight": "pytorch_model-00178-of-00243.bin",
|
| 406 |
+
"model.layers.44.self_attn.rotary_emb.inv_freq": "pytorch_model-00179-of-00243.bin",
|
| 407 |
+
"model.layers.44.self_attn.v_proj.weight": "pytorch_model-00179-of-00243.bin",
|
| 408 |
+
"model.layers.45.input_layernorm.weight": "pytorch_model-00186-of-00243.bin",
|
| 409 |
+
"model.layers.45.mlp.down_proj.weight": "pytorch_model-00185-of-00243.bin",
|
| 410 |
+
"model.layers.45.mlp.gate_proj.weight": "pytorch_model-00184-of-00243.bin",
|
| 411 |
+
"model.layers.45.mlp.up_proj.weight": "pytorch_model-00186-of-00243.bin",
|
| 412 |
+
"model.layers.45.post_attention_layernorm.weight": "pytorch_model-00186-of-00243.bin",
|
| 413 |
+
"model.layers.45.self_attn.k_proj.weight": "pytorch_model-00183-of-00243.bin",
|
| 414 |
+
"model.layers.45.self_attn.o_proj.weight": "pytorch_model-00183-of-00243.bin",
|
| 415 |
+
"model.layers.45.self_attn.q_proj.weight": "pytorch_model-00182-of-00243.bin",
|
| 416 |
+
"model.layers.45.self_attn.rotary_emb.inv_freq": "pytorch_model-00183-of-00243.bin",
|
| 417 |
+
"model.layers.45.self_attn.v_proj.weight": "pytorch_model-00183-of-00243.bin",
|
| 418 |
+
"model.layers.46.input_layernorm.weight": "pytorch_model-00190-of-00243.bin",
|
| 419 |
+
"model.layers.46.mlp.down_proj.weight": "pytorch_model-00189-of-00243.bin",
|
| 420 |
+
"model.layers.46.mlp.gate_proj.weight": "pytorch_model-00188-of-00243.bin",
|
| 421 |
+
"model.layers.46.mlp.up_proj.weight": "pytorch_model-00190-of-00243.bin",
|
| 422 |
+
"model.layers.46.post_attention_layernorm.weight": "pytorch_model-00190-of-00243.bin",
|
| 423 |
+
"model.layers.46.self_attn.k_proj.weight": "pytorch_model-00187-of-00243.bin",
|
| 424 |
+
"model.layers.46.self_attn.o_proj.weight": "pytorch_model-00187-of-00243.bin",
|
| 425 |
+
"model.layers.46.self_attn.q_proj.weight": "pytorch_model-00186-of-00243.bin",
|
| 426 |
+
"model.layers.46.self_attn.rotary_emb.inv_freq": "pytorch_model-00187-of-00243.bin",
|
| 427 |
+
"model.layers.46.self_attn.v_proj.weight": "pytorch_model-00187-of-00243.bin",
|
| 428 |
+
"model.layers.47.input_layernorm.weight": "pytorch_model-00194-of-00243.bin",
|
| 429 |
+
"model.layers.47.mlp.down_proj.weight": "pytorch_model-00193-of-00243.bin",
|
| 430 |
+
"model.layers.47.mlp.gate_proj.weight": "pytorch_model-00192-of-00243.bin",
|
| 431 |
+
"model.layers.47.mlp.up_proj.weight": "pytorch_model-00194-of-00243.bin",
|
| 432 |
+
"model.layers.47.post_attention_layernorm.weight": "pytorch_model-00194-of-00243.bin",
|
| 433 |
+
"model.layers.47.self_attn.k_proj.weight": "pytorch_model-00191-of-00243.bin",
|
| 434 |
+
"model.layers.47.self_attn.o_proj.weight": "pytorch_model-00191-of-00243.bin",
|
| 435 |
+
"model.layers.47.self_attn.q_proj.weight": "pytorch_model-00190-of-00243.bin",
|
| 436 |
+
"model.layers.47.self_attn.rotary_emb.inv_freq": "pytorch_model-00191-of-00243.bin",
|
| 437 |
+
"model.layers.47.self_attn.v_proj.weight": "pytorch_model-00191-of-00243.bin",
|
| 438 |
+
"model.layers.48.input_layernorm.weight": "pytorch_model-00198-of-00243.bin",
|
| 439 |
+
"model.layers.48.mlp.down_proj.weight": "pytorch_model-00197-of-00243.bin",
|
| 440 |
+
"model.layers.48.mlp.gate_proj.weight": "pytorch_model-00196-of-00243.bin",
|
| 441 |
+
"model.layers.48.mlp.up_proj.weight": "pytorch_model-00198-of-00243.bin",
|
| 442 |
+
"model.layers.48.post_attention_layernorm.weight": "pytorch_model-00198-of-00243.bin",
|
| 443 |
+
"model.layers.48.self_attn.k_proj.weight": "pytorch_model-00195-of-00243.bin",
|
| 444 |
+
"model.layers.48.self_attn.o_proj.weight": "pytorch_model-00195-of-00243.bin",
|
| 445 |
+
"model.layers.48.self_attn.q_proj.weight": "pytorch_model-00194-of-00243.bin",
|
| 446 |
+
"model.layers.48.self_attn.rotary_emb.inv_freq": "pytorch_model-00195-of-00243.bin",
|
| 447 |
+
"model.layers.48.self_attn.v_proj.weight": "pytorch_model-00195-of-00243.bin",
|
| 448 |
+
"model.layers.49.input_layernorm.weight": "pytorch_model-00202-of-00243.bin",
|
| 449 |
+
"model.layers.49.mlp.down_proj.weight": "pytorch_model-00201-of-00243.bin",
|
| 450 |
+
"model.layers.49.mlp.gate_proj.weight": "pytorch_model-00200-of-00243.bin",
|
| 451 |
+
"model.layers.49.mlp.up_proj.weight": "pytorch_model-00202-of-00243.bin",
|
| 452 |
+
"model.layers.49.post_attention_layernorm.weight": "pytorch_model-00202-of-00243.bin",
|
| 453 |
+
"model.layers.49.self_attn.k_proj.weight": "pytorch_model-00199-of-00243.bin",
|
| 454 |
+
"model.layers.49.self_attn.o_proj.weight": "pytorch_model-00199-of-00243.bin",
|
| 455 |
+
"model.layers.49.self_attn.q_proj.weight": "pytorch_model-00198-of-00243.bin",
|
| 456 |
+
"model.layers.49.self_attn.rotary_emb.inv_freq": "pytorch_model-00199-of-00243.bin",
|
| 457 |
+
"model.layers.49.self_attn.v_proj.weight": "pytorch_model-00199-of-00243.bin",
|
| 458 |
+
"model.layers.5.input_layernorm.weight": "pytorch_model-00026-of-00243.bin",
|
| 459 |
+
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00025-of-00243.bin",
|
| 460 |
+
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00024-of-00243.bin",
|
| 461 |
+
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00026-of-00243.bin",
|
| 462 |
+
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00026-of-00243.bin",
|
| 463 |
+
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00023-of-00243.bin",
|
| 464 |
+
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00023-of-00243.bin",
|
| 465 |
+
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00022-of-00243.bin",
|
| 466 |
+
"model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00023-of-00243.bin",
|
| 467 |
+
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00023-of-00243.bin",
|
| 468 |
+
"model.layers.50.input_layernorm.weight": "pytorch_model-00206-of-00243.bin",
|
| 469 |
+
"model.layers.50.mlp.down_proj.weight": "pytorch_model-00205-of-00243.bin",
|
| 470 |
+
"model.layers.50.mlp.gate_proj.weight": "pytorch_model-00204-of-00243.bin",
|
| 471 |
+
"model.layers.50.mlp.up_proj.weight": "pytorch_model-00206-of-00243.bin",
|
| 472 |
+
"model.layers.50.post_attention_layernorm.weight": "pytorch_model-00206-of-00243.bin",
|
| 473 |
+
"model.layers.50.self_attn.k_proj.weight": "pytorch_model-00203-of-00243.bin",
|
| 474 |
+
"model.layers.50.self_attn.o_proj.weight": "pytorch_model-00203-of-00243.bin",
|
| 475 |
+
"model.layers.50.self_attn.q_proj.weight": "pytorch_model-00202-of-00243.bin",
|
| 476 |
+
"model.layers.50.self_attn.rotary_emb.inv_freq": "pytorch_model-00203-of-00243.bin",
|
| 477 |
+
"model.layers.50.self_attn.v_proj.weight": "pytorch_model-00203-of-00243.bin",
|
| 478 |
+
"model.layers.51.input_layernorm.weight": "pytorch_model-00210-of-00243.bin",
|
| 479 |
+
"model.layers.51.mlp.down_proj.weight": "pytorch_model-00209-of-00243.bin",
|
| 480 |
+
"model.layers.51.mlp.gate_proj.weight": "pytorch_model-00208-of-00243.bin",
|
| 481 |
+
"model.layers.51.mlp.up_proj.weight": "pytorch_model-00210-of-00243.bin",
|
| 482 |
+
"model.layers.51.post_attention_layernorm.weight": "pytorch_model-00210-of-00243.bin",
|
| 483 |
+
"model.layers.51.self_attn.k_proj.weight": "pytorch_model-00207-of-00243.bin",
|
| 484 |
+
"model.layers.51.self_attn.o_proj.weight": "pytorch_model-00207-of-00243.bin",
|
| 485 |
+
"model.layers.51.self_attn.q_proj.weight": "pytorch_model-00206-of-00243.bin",
|
| 486 |
+
"model.layers.51.self_attn.rotary_emb.inv_freq": "pytorch_model-00207-of-00243.bin",
|
| 487 |
+
"model.layers.51.self_attn.v_proj.weight": "pytorch_model-00207-of-00243.bin",
|
| 488 |
+
"model.layers.52.input_layernorm.weight": "pytorch_model-00214-of-00243.bin",
|
| 489 |
+
"model.layers.52.mlp.down_proj.weight": "pytorch_model-00213-of-00243.bin",
|
| 490 |
+
"model.layers.52.mlp.gate_proj.weight": "pytorch_model-00212-of-00243.bin",
|
| 491 |
+
"model.layers.52.mlp.up_proj.weight": "pytorch_model-00214-of-00243.bin",
|
| 492 |
+
"model.layers.52.post_attention_layernorm.weight": "pytorch_model-00214-of-00243.bin",
|
| 493 |
+
"model.layers.52.self_attn.k_proj.weight": "pytorch_model-00211-of-00243.bin",
|
| 494 |
+
"model.layers.52.self_attn.o_proj.weight": "pytorch_model-00211-of-00243.bin",
|
| 495 |
+
"model.layers.52.self_attn.q_proj.weight": "pytorch_model-00210-of-00243.bin",
|
| 496 |
+
"model.layers.52.self_attn.rotary_emb.inv_freq": "pytorch_model-00211-of-00243.bin",
|
| 497 |
+
"model.layers.52.self_attn.v_proj.weight": "pytorch_model-00211-of-00243.bin",
|
| 498 |
+
"model.layers.53.input_layernorm.weight": "pytorch_model-00218-of-00243.bin",
|
| 499 |
+
"model.layers.53.mlp.down_proj.weight": "pytorch_model-00217-of-00243.bin",
|
| 500 |
+
"model.layers.53.mlp.gate_proj.weight": "pytorch_model-00216-of-00243.bin",
|
| 501 |
+
"model.layers.53.mlp.up_proj.weight": "pytorch_model-00218-of-00243.bin",
|
| 502 |
+
"model.layers.53.post_attention_layernorm.weight": "pytorch_model-00218-of-00243.bin",
|
| 503 |
+
"model.layers.53.self_attn.k_proj.weight": "pytorch_model-00215-of-00243.bin",
|
| 504 |
+
"model.layers.53.self_attn.o_proj.weight": "pytorch_model-00215-of-00243.bin",
|
| 505 |
+
"model.layers.53.self_attn.q_proj.weight": "pytorch_model-00214-of-00243.bin",
|
| 506 |
+
"model.layers.53.self_attn.rotary_emb.inv_freq": "pytorch_model-00215-of-00243.bin",
|
| 507 |
+
"model.layers.53.self_attn.v_proj.weight": "pytorch_model-00215-of-00243.bin",
|
| 508 |
+
"model.layers.54.input_layernorm.weight": "pytorch_model-00222-of-00243.bin",
|
| 509 |
+
"model.layers.54.mlp.down_proj.weight": "pytorch_model-00221-of-00243.bin",
|
| 510 |
+
"model.layers.54.mlp.gate_proj.weight": "pytorch_model-00220-of-00243.bin",
|
| 511 |
+
"model.layers.54.mlp.up_proj.weight": "pytorch_model-00222-of-00243.bin",
|
| 512 |
+
"model.layers.54.post_attention_layernorm.weight": "pytorch_model-00222-of-00243.bin",
|
| 513 |
+
"model.layers.54.self_attn.k_proj.weight": "pytorch_model-00219-of-00243.bin",
|
| 514 |
+
"model.layers.54.self_attn.o_proj.weight": "pytorch_model-00219-of-00243.bin",
|
| 515 |
+
"model.layers.54.self_attn.q_proj.weight": "pytorch_model-00218-of-00243.bin",
|
| 516 |
+
"model.layers.54.self_attn.rotary_emb.inv_freq": "pytorch_model-00219-of-00243.bin",
|
| 517 |
+
"model.layers.54.self_attn.v_proj.weight": "pytorch_model-00219-of-00243.bin",
|
| 518 |
+
"model.layers.55.input_layernorm.weight": "pytorch_model-00226-of-00243.bin",
|
| 519 |
+
"model.layers.55.mlp.down_proj.weight": "pytorch_model-00225-of-00243.bin",
|
| 520 |
+
"model.layers.55.mlp.gate_proj.weight": "pytorch_model-00224-of-00243.bin",
|
| 521 |
+
"model.layers.55.mlp.up_proj.weight": "pytorch_model-00226-of-00243.bin",
|
| 522 |
+
"model.layers.55.post_attention_layernorm.weight": "pytorch_model-00226-of-00243.bin",
|
| 523 |
+
"model.layers.55.self_attn.k_proj.weight": "pytorch_model-00223-of-00243.bin",
|
| 524 |
+
"model.layers.55.self_attn.o_proj.weight": "pytorch_model-00223-of-00243.bin",
|
| 525 |
+
"model.layers.55.self_attn.q_proj.weight": "pytorch_model-00222-of-00243.bin",
|
| 526 |
+
"model.layers.55.self_attn.rotary_emb.inv_freq": "pytorch_model-00223-of-00243.bin",
|
| 527 |
+
"model.layers.55.self_attn.v_proj.weight": "pytorch_model-00223-of-00243.bin",
|
| 528 |
+
"model.layers.56.input_layernorm.weight": "pytorch_model-00230-of-00243.bin",
|
| 529 |
+
"model.layers.56.mlp.down_proj.weight": "pytorch_model-00229-of-00243.bin",
|
| 530 |
+
"model.layers.56.mlp.gate_proj.weight": "pytorch_model-00228-of-00243.bin",
|
| 531 |
+
"model.layers.56.mlp.up_proj.weight": "pytorch_model-00230-of-00243.bin",
|
| 532 |
+
"model.layers.56.post_attention_layernorm.weight": "pytorch_model-00230-of-00243.bin",
|
| 533 |
+
"model.layers.56.self_attn.k_proj.weight": "pytorch_model-00227-of-00243.bin",
|
| 534 |
+
"model.layers.56.self_attn.o_proj.weight": "pytorch_model-00227-of-00243.bin",
|
| 535 |
+
"model.layers.56.self_attn.q_proj.weight": "pytorch_model-00226-of-00243.bin",
|
| 536 |
+
"model.layers.56.self_attn.rotary_emb.inv_freq": "pytorch_model-00227-of-00243.bin",
|
| 537 |
+
"model.layers.56.self_attn.v_proj.weight": "pytorch_model-00227-of-00243.bin",
|
| 538 |
+
"model.layers.57.input_layernorm.weight": "pytorch_model-00234-of-00243.bin",
|
| 539 |
+
"model.layers.57.mlp.down_proj.weight": "pytorch_model-00233-of-00243.bin",
|
| 540 |
+
"model.layers.57.mlp.gate_proj.weight": "pytorch_model-00232-of-00243.bin",
|
| 541 |
+
"model.layers.57.mlp.up_proj.weight": "pytorch_model-00234-of-00243.bin",
|
| 542 |
+
"model.layers.57.post_attention_layernorm.weight": "pytorch_model-00234-of-00243.bin",
|
| 543 |
+
"model.layers.57.self_attn.k_proj.weight": "pytorch_model-00231-of-00243.bin",
|
| 544 |
+
"model.layers.57.self_attn.o_proj.weight": "pytorch_model-00231-of-00243.bin",
|
| 545 |
+
"model.layers.57.self_attn.q_proj.weight": "pytorch_model-00230-of-00243.bin",
|
| 546 |
+
"model.layers.57.self_attn.rotary_emb.inv_freq": "pytorch_model-00231-of-00243.bin",
|
| 547 |
+
"model.layers.57.self_attn.v_proj.weight": "pytorch_model-00231-of-00243.bin",
|
| 548 |
+
"model.layers.58.input_layernorm.weight": "pytorch_model-00238-of-00243.bin",
|
| 549 |
+
"model.layers.58.mlp.down_proj.weight": "pytorch_model-00237-of-00243.bin",
|
| 550 |
+
"model.layers.58.mlp.gate_proj.weight": "pytorch_model-00236-of-00243.bin",
|
| 551 |
+
"model.layers.58.mlp.up_proj.weight": "pytorch_model-00238-of-00243.bin",
|
| 552 |
+
"model.layers.58.post_attention_layernorm.weight": "pytorch_model-00238-of-00243.bin",
|
| 553 |
+
"model.layers.58.self_attn.k_proj.weight": "pytorch_model-00235-of-00243.bin",
|
| 554 |
+
"model.layers.58.self_attn.o_proj.weight": "pytorch_model-00235-of-00243.bin",
|
| 555 |
+
"model.layers.58.self_attn.q_proj.weight": "pytorch_model-00234-of-00243.bin",
|
| 556 |
+
"model.layers.58.self_attn.rotary_emb.inv_freq": "pytorch_model-00235-of-00243.bin",
|
| 557 |
+
"model.layers.58.self_attn.v_proj.weight": "pytorch_model-00235-of-00243.bin",
|
| 558 |
+
"model.layers.59.input_layernorm.weight": "pytorch_model-00242-of-00243.bin",
|
| 559 |
+
"model.layers.59.mlp.down_proj.weight": "pytorch_model-00241-of-00243.bin",
|
| 560 |
+
"model.layers.59.mlp.gate_proj.weight": "pytorch_model-00240-of-00243.bin",
|
| 561 |
+
"model.layers.59.mlp.up_proj.weight": "pytorch_model-00242-of-00243.bin",
|
| 562 |
+
"model.layers.59.post_attention_layernorm.weight": "pytorch_model-00242-of-00243.bin",
|
| 563 |
+
"model.layers.59.self_attn.k_proj.weight": "pytorch_model-00239-of-00243.bin",
|
| 564 |
+
"model.layers.59.self_attn.o_proj.weight": "pytorch_model-00239-of-00243.bin",
|
| 565 |
+
"model.layers.59.self_attn.q_proj.weight": "pytorch_model-00238-of-00243.bin",
|
| 566 |
+
"model.layers.59.self_attn.rotary_emb.inv_freq": "pytorch_model-00239-of-00243.bin",
|
| 567 |
+
"model.layers.59.self_attn.v_proj.weight": "pytorch_model-00239-of-00243.bin",
|
| 568 |
+
"model.layers.6.input_layernorm.weight": "pytorch_model-00030-of-00243.bin",
|
| 569 |
+
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00029-of-00243.bin",
|
| 570 |
+
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00028-of-00243.bin",
|
| 571 |
+
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00030-of-00243.bin",
|
| 572 |
+
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00030-of-00243.bin",
|
| 573 |
+
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00027-of-00243.bin",
|
| 574 |
+
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00027-of-00243.bin",
|
| 575 |
+
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00026-of-00243.bin",
|
| 576 |
+
"model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00027-of-00243.bin",
|
| 577 |
+
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00027-of-00243.bin",
|
| 578 |
+
"model.layers.7.input_layernorm.weight": "pytorch_model-00034-of-00243.bin",
|
| 579 |
+
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00033-of-00243.bin",
|
| 580 |
+
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00032-of-00243.bin",
|
| 581 |
+
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00034-of-00243.bin",
|
| 582 |
+
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00034-of-00243.bin",
|
| 583 |
+
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00031-of-00243.bin",
|
| 584 |
+
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00031-of-00243.bin",
|
| 585 |
+
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00030-of-00243.bin",
|
| 586 |
+
"model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00031-of-00243.bin",
|
| 587 |
+
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00031-of-00243.bin",
|
| 588 |
+
"model.layers.8.input_layernorm.weight": "pytorch_model-00038-of-00243.bin",
|
| 589 |
+
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00037-of-00243.bin",
|
| 590 |
+
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00036-of-00243.bin",
|
| 591 |
+
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00038-of-00243.bin",
|
| 592 |
+
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00038-of-00243.bin",
|
| 593 |
+
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00035-of-00243.bin",
|
| 594 |
+
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00035-of-00243.bin",
|
| 595 |
+
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00034-of-00243.bin",
|
| 596 |
+
"model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00035-of-00243.bin",
|
| 597 |
+
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00035-of-00243.bin",
|
| 598 |
+
"model.layers.9.input_layernorm.weight": "pytorch_model-00042-of-00243.bin",
|
| 599 |
+
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00041-of-00243.bin",
|
| 600 |
+
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00040-of-00243.bin",
|
| 601 |
+
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00042-of-00243.bin",
|
| 602 |
+
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00042-of-00243.bin",
|
| 603 |
+
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00039-of-00243.bin",
|
| 604 |
+
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00039-of-00243.bin",
|
| 605 |
+
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00038-of-00243.bin",
|
| 606 |
+
"model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00039-of-00243.bin",
|
| 607 |
+
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00039-of-00243.bin",
|
| 608 |
+
"model.norm.weight": "pytorch_model-00242-of-00243.bin"
|
| 609 |
+
}
|
| 610 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"unk_token": {
|
| 17 |
+
"content": "<unk>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"bos_token": {
|
| 5 |
+
"__type": "AddedToken",
|
| 6 |
+
"content": "<s>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": true,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"clean_up_tokenization_spaces": false,
|
| 13 |
+
"eos_token": {
|
| 14 |
+
"__type": "AddedToken",
|
| 15 |
+
"content": "</s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": true,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false
|
| 20 |
+
},
|
| 21 |
+
"model_max_length": 2048,
|
| 22 |
+
"pad_token": null,
|
| 23 |
+
"sp_model_kwargs": {},
|
| 24 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 25 |
+
"unk_token": {
|
| 26 |
+
"__type": "AddedToken",
|
| 27 |
+
"content": "<unk>",
|
| 28 |
+
"lstrip": false,
|
| 29 |
+
"normalized": true,
|
| 30 |
+
"rstrip": false,
|
| 31 |
+
"single_word": false
|
| 32 |
+
}
|
| 33 |
+
}
|