commit 67bbf87988831cc3a4e1d23e92e9a79e9d803a0c Author: ModelHub XC Date: Fri Sep 4 01:54:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: sag-uniroma2/extremITA-Camoscio-7b Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a6344aa --- /dev/null +++ b/.gitattributes @@ -0,0 +1,35 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..3b5cb2c --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +inference: false +license: openrail +language: +- it +datasets: +- teelinsan/camoscio +--- + +# ExtremITA Camoscio 7 bilion parameters +This is the base model trained on Italian instructions, a sibling of Alpaca. +It is based on [tellinsan/camoscio-7b-llama](https://huggingface.co/teelinsan/camoscio-7b-llama) adapters and the original LLaMA model, and it adds nothing new to [tellinsan/camoscio-7b-llama](https://huggingface.co/teelinsan/camoscio-7b-llama). Our version is the merged model with the adapters in order to obtain a more stable model that can be further fine-tuned, which we did for the [EVALITA 2023](https://www.evalita.it/campaigns/evalita-2023/) challenge. + +# Usage +Checkout the github repository for more insights and codes: https://github.com/crux82/ExtremITA + +```python +from transformers import LLaMATokenizer, LLaMAForCausalLM, GenerationConfig +import torch + +tokenizer = LLaMATokenizer.from_pretrained("yahma/llama-7b-hf") +model = LLaMAForCausalLM.from_pretrained( + "sag-uniroma2/extremITA-Camoscio-7b", + load_in_8bit=True, + device_map="auto", +) + +generation_config = GenerationConfig( + temperature=0.2, + top_p=0.75, + top_k=40, + num_beams=4, +) + +prompts = [ + "Riassumi la storia di Pinocchio", + "Scrivi un programma che stampa i numeri da 1 a 100. Ma per i multipli \ + di tre stampa 'Fizz' al posto del numero e per i multipli di cinque \ + stampa 'Buzz'. Per i numeri che sono multipli sia di tre che di cinque \ + stampa 'FizzBuzz'." +] + +inputs = tokenizer(prompts, return_tensors="pt", padding=True, \ + truncation=True).to(model.device) + +with torch.no_grad(): + gen_outputs = model.generate( + **inputs, + generation_config=generation_config, + return_dict_in_generate=True, + output_scores=True, + ) + + for i in range(len(gen_outputs[0])): + output = tokenizer.decode(gen_outputs[0][i], skip_special_tokens=True) + print(output) +``` + +# Citation +``` +@inproceedings{hromei2023extremita, + author = {Claudiu Daniel Hromei and + Danilo Croce and + Valerio Basile and + Roberto Basili}, + title = {ExtremITA at EVALITA 2023: Multi-Task Sustainable Scaling to Large Language Models at its Extreme}, + booktitle = {Proceedings of the Eighth Evaluation Campaign of Natural Language + Processing and Speech Tools for Italian. Final Workshop (EVALITA 2023)}, + publisher = {CEUR.org}, + year = {2023}, + month = {September}, + address = {Parma, Italy} +} +``` diff --git a/config.json b/config.json new file mode 100644 index 0000000..62409fc --- /dev/null +++ b/config.json @@ -0,0 +1,24 @@ +{ + "_name_or_path": "decapoda-research/llama-7b-hf", + "architectures": [ + "LlamaForCausalLM" + ], + "bos_token_id": 0, + "eos_token_id": 1, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 11008, + "max_position_embeddings": 2048, + "max_sequence_length": 2048, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "pad_token_id": -1, + "rms_norm_eps": 1e-06, + "tie_word_embeddings": false, + "torch_dtype": "float16", + "transformers_version": "4.29.0.dev0", + "use_cache": true, + "vocab_size": 32000 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..28d380f --- /dev/null +++ b/generation_config.json @@ -0,0 +1,7 @@ +{ + "_from_model_config": true, + "bos_token_id": 0, + "eos_token_id": 1, + "pad_token_id": 0, + "transformers_version": "4.29.0.dev0" +} diff --git a/pytorch_model-00001-of-00039.bin b/pytorch_model-00001-of-00039.bin new file mode 100644 index 0000000..e797c9e --- /dev/null +++ b/pytorch_model-00001-of-00039.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5a32cc9135dc8931a597372eaa350a858e18826799c820f57445a7d6b5e0171 +size 396364479 diff --git a/pytorch_model-00002-of-00039.bin b/pytorch_model-00002-of-00039.bin new file mode 100644 index 0000000..cd697ab --- /dev/null +++ b/pytorch_model-00002-of-00039.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97c6349da4476422d9b2b7dc4299ebf1c500b5d7ec327ba5e635439663f0dfb0 +size 371215393 diff --git a/pytorch_model-00003-of-00039.bin b/pytorch_model-00003-of-00039.bin new file mode 100644 index 0000000..984bcb1 --- /dev/null +++ b/pytorch_model-00003-of-00039.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5fd1fc1fd5f1473cdd55ee564fd06f8477faf2e0417654f9624ec9d7c32d3f0 +size 371215986 diff --git a/pytorch_model-00004-of-00039.bin b/pytorch_model-00004-of-00039.bin new file mode 100644 index 0000000..1581bac --- /dev/null +++ b/pytorch_model-00004-of-00039.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c30b573866a06f59e01c24289b9610c620d4c8aeb319a741f771817ac2351b65 +size 371215986 diff --git a/pytorch_model-00005-of-00039.bin b/pytorch_model-00005-of-00039.bin new file mode 100644 index 0000000..503f61d --- /dev/null +++ b/pytorch_model-00005-of-00039.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41ad151e04be4776b386346f59438a86b442877b934a2a8af3895d8674672e51 +size 371215986 diff --git a/pytorch_model-00006-of-00039.bin b/pytorch_model-00006-of-00039.bin new file mode 100644 index 0000000..90a229f --- /dev/null +++ b/pytorch_model-00006-of-00039.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d112591c695bef40edb7cd45ffbb57bde077e9f902f59224d695abc175cb8160 +size 314575888 diff --git a/pytorch_model-00007-of-00039.bin b/pytorch_model-00007-of-00039.bin new file mode 100644 index 0000000..991e90f --- /dev/null +++ b/pytorch_model-00007-of-00039.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91d64cf351f466408d91e6afd8bc6f9218644d1d52b7b154af04263d841e31a0 +size 314592882 diff --git a/pytorch_model-00008-of-00039.bin b/pytorch_model-00008-of-00039.bin new file mode 100644 index 0000000..cdd9559 --- /dev/null +++ b/pytorch_model-00008-of-00039.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84cfde3d94b6d2ae5deddb0ff463074057bc6e17bc8f30e078d2c45bc3e9befa +size 314592882 diff --git a/pytorch_model-00009-of-00039.bin b/pytorch_model-00009-of-00039.bin new file mode 100644 index 0000000..d65544d --- /dev/null +++ b/pytorch_model-00009-of-00039.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e5a5848794ad1377a3ec62141a532eaf0c1dfdc7e4bfe278ad3496716852e2d +size 371215393 diff --git a/pytorch_model-00010-of-00039.bin b/pytorch_model-00010-of-00039.bin new file mode 100644 index 0000000..c19761b --- /dev/null +++ b/pytorch_model-00010-of-00039.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25979ac548cb35334835f51bbb524033fd8f4a6cb91003d2fe61581093496f60 +size 371215986 diff --git a/pytorch_model-00011-of-00039.bin b/pytorch_model-00011-of-00039.bin new file mode 100644 index 0000000..a2b29de --- /dev/null +++ b/pytorch_model-00011-of-00039.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbc10b5f401d831fabbee77bd166dfe0945304b08c0fd5c9dbfd6cad1725e414 +size 371215986 diff --git a/pytorch_model-00012-of-00039.bin b/pytorch_model-00012-of-00039.bin new file mode 100644 index 0000000..b5b29af --- /dev/null +++ b/pytorch_model-00012-of-00039.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd02280662be680e96e6fe395fef6b21739ace77abe60d7c15cb0d346974c505 +size 371215986 diff --git a/pytorch_model-00013-of-00039.bin b/pytorch_model-00013-of-00039.bin new file mode 100644 index 0000000..265f180 --- /dev/null +++ b/pytorch_model-00013-of-00039.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8533020871e5b909ecf892f1035e39c6b7343bd43e4db407f816f2ab213e5918 +size 314575888 diff --git a/pytorch_model-00014-of-00039.bin b/pytorch_model-00014-of-00039.bin new file mode 100644 index 0000000..12d6a4d --- /dev/null +++ b/pytorch_model-00014-of-00039.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2dcfd873e70d89f5ddd629a77fdb2476b81a40f3539ed92310c8214b1162cadd +size 314592882 diff --git a/pytorch_model-00015-of-00039.bin b/pytorch_model-00015-of-00039.bin new file mode 100644 index 0000000..c8e02cb --- /dev/null +++ b/pytorch_model-00015-of-00039.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db97fa713d05460ef72c73456d48817c349bf455ece351d8da24d5e9da9a0797 +size 314592882 diff --git a/pytorch_model-00016-of-00039.bin b/pytorch_model-00016-of-00039.bin new file mode 100644 index 0000000..b777d41 --- /dev/null +++ b/pytorch_model-00016-of-00039.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ff774c1ee2f0ebd16e31172bf3e604cc70b2c8034dd7b45a9aac0a85db754d8 +size 371215393 diff --git a/pytorch_model-00017-of-00039.bin b/pytorch_model-00017-of-00039.bin new file mode 100644 index 0000000..59d2092 --- /dev/null +++ b/pytorch_model-00017-of-00039.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2792857253b9c9bb2e4309e46701593b30fba2e7add357fb956c5b90b924304 +size 371215986 diff --git a/pytorch_model-00018-of-00039.bin b/pytorch_model-00018-of-00039.bin new file mode 100644 index 0000000..620afb2 --- /dev/null +++ b/pytorch_model-00018-of-00039.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1c9ebd0042a7b7773bc403f1746127a5297a5090bbc6e9547676412e538c955 +size 371215986 diff --git a/pytorch_model-00019-of-00039.bin b/pytorch_model-00019-of-00039.bin new file mode 100644 index 0000000..3934bd9 --- /dev/null +++ b/pytorch_model-00019-of-00039.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2ac563c53bd83e912e3a41b483d4c8bf740040d25161a9068815cad0a65b750 +size 371215986 diff --git a/pytorch_model-00020-of-00039.bin b/pytorch_model-00020-of-00039.bin new file mode 100644 index 0000000..32bcd5a --- /dev/null +++ b/pytorch_model-00020-of-00039.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07ab06c583caad46b0cf10ea90addcf254a30eb932728ed122cd1e3fdb131372 +size 314575888 diff --git a/pytorch_model-00021-of-00039.bin b/pytorch_model-00021-of-00039.bin new file mode 100644 index 0000000..489fa42 --- /dev/null +++ b/pytorch_model-00021-of-00039.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d83f6404b19dcb58932e19b7a71029138fa915f6aa6ef730463c30f419bcf652 +size 314592882 diff --git a/pytorch_model-00022-of-00039.bin b/pytorch_model-00022-of-00039.bin new file mode 100644 index 0000000..981c8fa --- /dev/null +++ b/pytorch_model-00022-of-00039.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bac1f2b89d59c33bfbba5527930e6891f0a87146a7433a24720df55849ab5faa +size 314592882 diff --git a/pytorch_model-00023-of-00039.bin b/pytorch_model-00023-of-00039.bin new file mode 100644 index 0000000..b4d1ddf --- /dev/null +++ b/pytorch_model-00023-of-00039.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b9b738ea6083df5ead0978d99488ea63af42569afa5d3cb05a0a922a5b1d57d +size 371215393 diff --git a/pytorch_model-00024-of-00039.bin b/pytorch_model-00024-of-00039.bin new file mode 100644 index 0000000..77e3d7d --- /dev/null +++ b/pytorch_model-00024-of-00039.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4ce3a929b6978ed96b852ccffbd1431161673c9cf0d100e801d1732632adeb8 +size 371215986 diff --git a/pytorch_model-00025-of-00039.bin b/pytorch_model-00025-of-00039.bin new file mode 100644 index 0000000..cbee219 --- /dev/null +++ b/pytorch_model-00025-of-00039.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c476535beb72060a308bb69e0c4bf4eb904ef9defe0a64d88832c6e231774c84 +size 371215986 diff --git a/pytorch_model-00026-of-00039.bin b/pytorch_model-00026-of-00039.bin new file mode 100644 index 0000000..e95212e --- /dev/null +++ b/pytorch_model-00026-of-00039.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86dea8014bc56acb23c2970ce802d78b36e8302154a1e87d28740ec0a6d08b90 +size 371215986 diff --git a/pytorch_model-00027-of-00039.bin b/pytorch_model-00027-of-00039.bin new file mode 100644 index 0000000..b93da8c --- /dev/null +++ b/pytorch_model-00027-of-00039.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:757e271a5f779424a33407538715b8a3c4f9e485932d7642ffc2b31609ff432c +size 314575888 diff --git a/pytorch_model-00028-of-00039.bin b/pytorch_model-00028-of-00039.bin new file mode 100644 index 0000000..1f46fba --- /dev/null +++ b/pytorch_model-00028-of-00039.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1bfb85d81d8e15e1ac58bd671b19777e542199f4b68f457af39117cfc987c700 +size 314592882 diff --git a/pytorch_model-00029-of-00039.bin b/pytorch_model-00029-of-00039.bin new file mode 100644 index 0000000..7b5cecc --- /dev/null +++ b/pytorch_model-00029-of-00039.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:512121431dd5348b874c91bb34015ecb6de6b2023f5e1977535938aa1af08c05 +size 314592882 diff --git a/pytorch_model-00030-of-00039.bin b/pytorch_model-00030-of-00039.bin new file mode 100644 index 0000000..af0c94e --- /dev/null +++ b/pytorch_model-00030-of-00039.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27ab788ef2d8e69d0d26bd8c0fae44ae7f1ce4b83587cabaf6298e22efa2a0ef +size 371215393 diff --git a/pytorch_model-00031-of-00039.bin b/pytorch_model-00031-of-00039.bin new file mode 100644 index 0000000..fd842bb --- /dev/null +++ b/pytorch_model-00031-of-00039.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a0e3f4966a137b4a28e200b2f303b9b40fd247896b310f97e11364f60f3e894 +size 371215986 diff --git a/pytorch_model-00032-of-00039.bin b/pytorch_model-00032-of-00039.bin new file mode 100644 index 0000000..35cd851 --- /dev/null +++ b/pytorch_model-00032-of-00039.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac1a2167cbe65c4cb0257a498af46d9016d953914afb4cb47137160a5f8759ca +size 371215986 diff --git a/pytorch_model-00033-of-00039.bin b/pytorch_model-00033-of-00039.bin new file mode 100644 index 0000000..fcfd8f4 --- /dev/null +++ b/pytorch_model-00033-of-00039.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eabd7a093d726ade4eecfe7ad5004a9e2caf7285dad431368e9b45ea141ee934 +size 371215986 diff --git a/pytorch_model-00034-of-00039.bin b/pytorch_model-00034-of-00039.bin new file mode 100644 index 0000000..9ba1258 --- /dev/null +++ b/pytorch_model-00034-of-00039.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ece2f30f159a2b82a0340ab6bed5a409c42629f5de7f6c068a09e53af8e81807 +size 314575888 diff --git a/pytorch_model-00035-of-00039.bin b/pytorch_model-00035-of-00039.bin new file mode 100644 index 0000000..cbcf33c --- /dev/null +++ b/pytorch_model-00035-of-00039.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:438b849a4a18bd5e13bb938119bd08b0c94b8f781a22f188e306e92ece8ccb8e +size 314592882 diff --git a/pytorch_model-00036-of-00039.bin b/pytorch_model-00036-of-00039.bin new file mode 100644 index 0000000..e7a80a8 --- /dev/null +++ b/pytorch_model-00036-of-00039.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eeb39640d77feb63e30d07ba0e215a74fbb16ef0dacfa431d0f6c17986ae5e3a +size 314592882 diff --git a/pytorch_model-00037-of-00039.bin b/pytorch_model-00037-of-00039.bin new file mode 100644 index 0000000..6552251 --- /dev/null +++ b/pytorch_model-00037-of-00039.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f41fc061ab5546dc2cb934c06537c3459e6e262e345129811eb4d47629909f1 +size 371215393 diff --git a/pytorch_model-00038-of-00039.bin b/pytorch_model-00038-of-00039.bin new file mode 100644 index 0000000..62fc982 --- /dev/null +++ b/pytorch_model-00038-of-00039.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6762c675eb30868665ce8ada7a2bbbd117e02f44d47ba3c8dcf91f5623e5ce67 +size 304114977 diff --git a/pytorch_model-00039-of-00039.bin b/pytorch_model-00039-of-00039.bin new file mode 100644 index 0000000..560e955 --- /dev/null +++ b/pytorch_model-00039-of-00039.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3350fb71c2bc1e88d77d9685716fd2759e879137814a4120d98265a43f405919 +size 262144938 diff --git a/pytorch_model.bin.index.json b/pytorch_model.bin.index.json new file mode 100644 index 0000000..37bef09 --- /dev/null +++ b/pytorch_model.bin.index.json @@ -0,0 +1,330 @@ +{ + "metadata": { + "total_size": 13476839424 + }, + "weight_map": { + "lm_head.weight": "pytorch_model-00039-of-00039.bin", + "model.embed_tokens.weight": "pytorch_model-00001-of-00039.bin", + "model.layers.0.input_layernorm.weight": "pytorch_model-00002-of-00039.bin", + "model.layers.0.mlp.down_proj.weight": "pytorch_model-00002-of-00039.bin", + "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00002-of-00039.bin", + "model.layers.0.mlp.up_proj.weight": "pytorch_model-00002-of-00039.bin", + "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00002-of-00039.bin", + "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00039.bin", + "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00039.bin", + "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00039.bin", + "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00039.bin", + "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00039.bin", + "model.layers.1.input_layernorm.weight": "pytorch_model-00003-of-00039.bin", + "model.layers.1.mlp.down_proj.weight": "pytorch_model-00003-of-00039.bin", + "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00003-of-00039.bin", + "model.layers.1.mlp.up_proj.weight": "pytorch_model-00003-of-00039.bin", + "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00003-of-00039.bin", + "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00002-of-00039.bin", + "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00003-of-00039.bin", + "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00002-of-00039.bin", + "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00039.bin", + "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00002-of-00039.bin", + "model.layers.10.input_layernorm.weight": "pytorch_model-00014-of-00039.bin", + "model.layers.10.mlp.down_proj.weight": "pytorch_model-00013-of-00039.bin", + "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00013-of-00039.bin", + "model.layers.10.mlp.up_proj.weight": "pytorch_model-00014-of-00039.bin", + "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00014-of-00039.bin", + "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00013-of-00039.bin", + "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00013-of-00039.bin", + "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00013-of-00039.bin", + "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00039.bin", + "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00013-of-00039.bin", + "model.layers.11.input_layernorm.weight": "pytorch_model-00015-of-00039.bin", + "model.layers.11.mlp.down_proj.weight": "pytorch_model-00015-of-00039.bin", + "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00014-of-00039.bin", + "model.layers.11.mlp.up_proj.weight": "pytorch_model-00015-of-00039.bin", + "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00015-of-00039.bin", + "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00014-of-00039.bin", + "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00014-of-00039.bin", + "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00014-of-00039.bin", + "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00014-of-00039.bin", + "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00014-of-00039.bin", + "model.layers.12.input_layernorm.weight": "pytorch_model-00016-of-00039.bin", + "model.layers.12.mlp.down_proj.weight": "pytorch_model-00016-of-00039.bin", + "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00016-of-00039.bin", + "model.layers.12.mlp.up_proj.weight": "pytorch_model-00016-of-00039.bin", + "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00016-of-00039.bin", + "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00015-of-00039.bin", + "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00015-of-00039.bin", + "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00015-of-00039.bin", + "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00015-of-00039.bin", + "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00015-of-00039.bin", + "model.layers.13.input_layernorm.weight": "pytorch_model-00017-of-00039.bin", + "model.layers.13.mlp.down_proj.weight": "pytorch_model-00017-of-00039.bin", + "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00017-of-00039.bin", + "model.layers.13.mlp.up_proj.weight": "pytorch_model-00017-of-00039.bin", + "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00017-of-00039.bin", + "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00016-of-00039.bin", + "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00017-of-00039.bin", + "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00016-of-00039.bin", + "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00017-of-00039.bin", + "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00016-of-00039.bin", + "model.layers.14.input_layernorm.weight": "pytorch_model-00018-of-00039.bin", + "model.layers.14.mlp.down_proj.weight": "pytorch_model-00018-of-00039.bin", + "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00018-of-00039.bin", + "model.layers.14.mlp.up_proj.weight": "pytorch_model-00018-of-00039.bin", + "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00018-of-00039.bin", + "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00017-of-00039.bin", + "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00018-of-00039.bin", + "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00017-of-00039.bin", + "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00018-of-00039.bin", + "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00018-of-00039.bin", + "model.layers.15.input_layernorm.weight": "pytorch_model-00019-of-00039.bin", + "model.layers.15.mlp.down_proj.weight": "pytorch_model-00019-of-00039.bin", + "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00019-of-00039.bin", + "model.layers.15.mlp.up_proj.weight": "pytorch_model-00019-of-00039.bin", + "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00019-of-00039.bin", + "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00019-of-00039.bin", + "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00019-of-00039.bin", + "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00018-of-00039.bin", + "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00019-of-00039.bin", + "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00019-of-00039.bin", + "model.layers.16.input_layernorm.weight": "pytorch_model-00021-of-00039.bin", + "model.layers.16.mlp.down_proj.weight": "pytorch_model-00020-of-00039.bin", + "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00020-of-00039.bin", + "model.layers.16.mlp.up_proj.weight": "pytorch_model-00021-of-00039.bin", + "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00021-of-00039.bin", + "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00020-of-00039.bin", + "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00020-of-00039.bin", + "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00020-of-00039.bin", + "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00020-of-00039.bin", + "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00020-of-00039.bin", + "model.layers.17.input_layernorm.weight": "pytorch_model-00022-of-00039.bin", + "model.layers.17.mlp.down_proj.weight": "pytorch_model-00022-of-00039.bin", + "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00021-of-00039.bin", + "model.layers.17.mlp.up_proj.weight": "pytorch_model-00022-of-00039.bin", + "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00022-of-00039.bin", + "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00021-of-00039.bin", + "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00021-of-00039.bin", + "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00021-of-00039.bin", + "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00021-of-00039.bin", + "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00021-of-00039.bin", + "model.layers.18.input_layernorm.weight": "pytorch_model-00023-of-00039.bin", + "model.layers.18.mlp.down_proj.weight": "pytorch_model-00023-of-00039.bin", + "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00023-of-00039.bin", + "model.layers.18.mlp.up_proj.weight": "pytorch_model-00023-of-00039.bin", + "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00023-of-00039.bin", + "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00022-of-00039.bin", + "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00022-of-00039.bin", + "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00022-of-00039.bin", + "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00022-of-00039.bin", + "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00022-of-00039.bin", + "model.layers.19.input_layernorm.weight": "pytorch_model-00024-of-00039.bin", + "model.layers.19.mlp.down_proj.weight": "pytorch_model-00024-of-00039.bin", + "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00024-of-00039.bin", + "model.layers.19.mlp.up_proj.weight": "pytorch_model-00024-of-00039.bin", + "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00024-of-00039.bin", + "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00023-of-00039.bin", + "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00024-of-00039.bin", + "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00023-of-00039.bin", + "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00024-of-00039.bin", + "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00023-of-00039.bin", + "model.layers.2.input_layernorm.weight": "pytorch_model-00004-of-00039.bin", + "model.layers.2.mlp.down_proj.weight": "pytorch_model-00004-of-00039.bin", + "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00004-of-00039.bin", + "model.layers.2.mlp.up_proj.weight": "pytorch_model-00004-of-00039.bin", + "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00004-of-00039.bin", + "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00003-of-00039.bin", + "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00004-of-00039.bin", + "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00003-of-00039.bin", + "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00039.bin", + "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00004-of-00039.bin", + "model.layers.20.input_layernorm.weight": "pytorch_model-00025-of-00039.bin", + "model.layers.20.mlp.down_proj.weight": "pytorch_model-00025-of-00039.bin", + "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00025-of-00039.bin", + "model.layers.20.mlp.up_proj.weight": "pytorch_model-00025-of-00039.bin", + "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00025-of-00039.bin", + "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00024-of-00039.bin", + "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00025-of-00039.bin", + "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00024-of-00039.bin", + "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00025-of-00039.bin", + "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00025-of-00039.bin", + "model.layers.21.input_layernorm.weight": "pytorch_model-00026-of-00039.bin", + "model.layers.21.mlp.down_proj.weight": "pytorch_model-00026-of-00039.bin", + "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00026-of-00039.bin", + "model.layers.21.mlp.up_proj.weight": "pytorch_model-00026-of-00039.bin", + "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00026-of-00039.bin", + "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00026-of-00039.bin", + "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00026-of-00039.bin", + "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00025-of-00039.bin", + "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00026-of-00039.bin", + "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00026-of-00039.bin", + "model.layers.22.input_layernorm.weight": "pytorch_model-00028-of-00039.bin", + "model.layers.22.mlp.down_proj.weight": "pytorch_model-00027-of-00039.bin", + "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00027-of-00039.bin", + "model.layers.22.mlp.up_proj.weight": "pytorch_model-00028-of-00039.bin", + "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00028-of-00039.bin", + "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00027-of-00039.bin", + "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00027-of-00039.bin", + "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00027-of-00039.bin", + "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00027-of-00039.bin", + "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00027-of-00039.bin", + "model.layers.23.input_layernorm.weight": "pytorch_model-00029-of-00039.bin", + "model.layers.23.mlp.down_proj.weight": "pytorch_model-00029-of-00039.bin", + "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00028-of-00039.bin", + "model.layers.23.mlp.up_proj.weight": "pytorch_model-00029-of-00039.bin", + "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00029-of-00039.bin", + "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00028-of-00039.bin", + "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00028-of-00039.bin", + "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00028-of-00039.bin", + "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00028-of-00039.bin", + "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00028-of-00039.bin", + "model.layers.24.input_layernorm.weight": "pytorch_model-00030-of-00039.bin", + "model.layers.24.mlp.down_proj.weight": "pytorch_model-00030-of-00039.bin", + "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00030-of-00039.bin", + "model.layers.24.mlp.up_proj.weight": "pytorch_model-00030-of-00039.bin", + "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00030-of-00039.bin", + "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00029-of-00039.bin", + "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00029-of-00039.bin", + "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00029-of-00039.bin", + "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00029-of-00039.bin", + "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00029-of-00039.bin", + "model.layers.25.input_layernorm.weight": "pytorch_model-00031-of-00039.bin", + "model.layers.25.mlp.down_proj.weight": "pytorch_model-00031-of-00039.bin", + "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00031-of-00039.bin", + "model.layers.25.mlp.up_proj.weight": "pytorch_model-00031-of-00039.bin", + "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00031-of-00039.bin", + "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00030-of-00039.bin", + "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00031-of-00039.bin", + "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00030-of-00039.bin", + "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00031-of-00039.bin", + "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00030-of-00039.bin", + "model.layers.26.input_layernorm.weight": "pytorch_model-00032-of-00039.bin", + "model.layers.26.mlp.down_proj.weight": "pytorch_model-00032-of-00039.bin", + "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00032-of-00039.bin", + "model.layers.26.mlp.up_proj.weight": "pytorch_model-00032-of-00039.bin", + "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00032-of-00039.bin", + "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00031-of-00039.bin", + "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00032-of-00039.bin", + "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00031-of-00039.bin", + "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00032-of-00039.bin", + "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00032-of-00039.bin", + "model.layers.27.input_layernorm.weight": "pytorch_model-00033-of-00039.bin", + "model.layers.27.mlp.down_proj.weight": "pytorch_model-00033-of-00039.bin", + "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00033-of-00039.bin", + "model.layers.27.mlp.up_proj.weight": "pytorch_model-00033-of-00039.bin", + "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00033-of-00039.bin", + "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00033-of-00039.bin", + "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00033-of-00039.bin", + "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00032-of-00039.bin", + "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00033-of-00039.bin", + "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00033-of-00039.bin", + "model.layers.28.input_layernorm.weight": "pytorch_model-00035-of-00039.bin", + "model.layers.28.mlp.down_proj.weight": "pytorch_model-00034-of-00039.bin", + "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00034-of-00039.bin", + "model.layers.28.mlp.up_proj.weight": "pytorch_model-00035-of-00039.bin", + "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00035-of-00039.bin", + "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00034-of-00039.bin", + "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00034-of-00039.bin", + "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00034-of-00039.bin", + "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00034-of-00039.bin", + "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00034-of-00039.bin", + "model.layers.29.input_layernorm.weight": "pytorch_model-00036-of-00039.bin", + "model.layers.29.mlp.down_proj.weight": "pytorch_model-00036-of-00039.bin", + "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00035-of-00039.bin", + "model.layers.29.mlp.up_proj.weight": "pytorch_model-00036-of-00039.bin", + "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00036-of-00039.bin", + "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00035-of-00039.bin", + "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00035-of-00039.bin", + "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00035-of-00039.bin", + "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00035-of-00039.bin", + "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00035-of-00039.bin", + "model.layers.3.input_layernorm.weight": "pytorch_model-00005-of-00039.bin", + "model.layers.3.mlp.down_proj.weight": "pytorch_model-00005-of-00039.bin", + "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00005-of-00039.bin", + "model.layers.3.mlp.up_proj.weight": "pytorch_model-00005-of-00039.bin", + "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00005-of-00039.bin", + "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00005-of-00039.bin", + "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00005-of-00039.bin", + "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00004-of-00039.bin", + "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00039.bin", + "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00005-of-00039.bin", + "model.layers.30.input_layernorm.weight": "pytorch_model-00037-of-00039.bin", + "model.layers.30.mlp.down_proj.weight": "pytorch_model-00037-of-00039.bin", + "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00037-of-00039.bin", + "model.layers.30.mlp.up_proj.weight": "pytorch_model-00037-of-00039.bin", + "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00037-of-00039.bin", + "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00036-of-00039.bin", + "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00036-of-00039.bin", + "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00036-of-00039.bin", + "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00036-of-00039.bin", + "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00036-of-00039.bin", + "model.layers.31.input_layernorm.weight": "pytorch_model-00038-of-00039.bin", + "model.layers.31.mlp.down_proj.weight": "pytorch_model-00038-of-00039.bin", + "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00038-of-00039.bin", + "model.layers.31.mlp.up_proj.weight": "pytorch_model-00038-of-00039.bin", + "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00038-of-00039.bin", + "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00037-of-00039.bin", + "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00038-of-00039.bin", + "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00037-of-00039.bin", + "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00038-of-00039.bin", + "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00037-of-00039.bin", + "model.layers.4.input_layernorm.weight": "pytorch_model-00007-of-00039.bin", + "model.layers.4.mlp.down_proj.weight": "pytorch_model-00006-of-00039.bin", + "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00006-of-00039.bin", + "model.layers.4.mlp.up_proj.weight": "pytorch_model-00007-of-00039.bin", + "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00007-of-00039.bin", + "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00006-of-00039.bin", + "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00006-of-00039.bin", + "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00006-of-00039.bin", + "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00039.bin", + "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00006-of-00039.bin", + "model.layers.5.input_layernorm.weight": "pytorch_model-00008-of-00039.bin", + "model.layers.5.mlp.down_proj.weight": "pytorch_model-00008-of-00039.bin", + "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00007-of-00039.bin", + "model.layers.5.mlp.up_proj.weight": "pytorch_model-00008-of-00039.bin", + "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00008-of-00039.bin", + "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00007-of-00039.bin", + "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00007-of-00039.bin", + "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00007-of-00039.bin", + "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00039.bin", + "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00007-of-00039.bin", + "model.layers.6.input_layernorm.weight": "pytorch_model-00009-of-00039.bin", + "model.layers.6.mlp.down_proj.weight": "pytorch_model-00009-of-00039.bin", + "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00009-of-00039.bin", + "model.layers.6.mlp.up_proj.weight": "pytorch_model-00009-of-00039.bin", + "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00009-of-00039.bin", + "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00008-of-00039.bin", + "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00008-of-00039.bin", + "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00008-of-00039.bin", + "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00039.bin", + "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00008-of-00039.bin", + "model.layers.7.input_layernorm.weight": "pytorch_model-00010-of-00039.bin", + "model.layers.7.mlp.down_proj.weight": "pytorch_model-00010-of-00039.bin", + "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00010-of-00039.bin", + "model.layers.7.mlp.up_proj.weight": "pytorch_model-00010-of-00039.bin", + "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00010-of-00039.bin", + "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00009-of-00039.bin", + "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00010-of-00039.bin", + "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00009-of-00039.bin", + "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00039.bin", + "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00009-of-00039.bin", + "model.layers.8.input_layernorm.weight": "pytorch_model-00011-of-00039.bin", + "model.layers.8.mlp.down_proj.weight": "pytorch_model-00011-of-00039.bin", + "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00011-of-00039.bin", + "model.layers.8.mlp.up_proj.weight": "pytorch_model-00011-of-00039.bin", + "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00011-of-00039.bin", + "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00010-of-00039.bin", + "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00011-of-00039.bin", + "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00010-of-00039.bin", + "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00039.bin", + "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00011-of-00039.bin", + "model.layers.9.input_layernorm.weight": "pytorch_model-00012-of-00039.bin", + "model.layers.9.mlp.down_proj.weight": "pytorch_model-00012-of-00039.bin", + "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00012-of-00039.bin", + "model.layers.9.mlp.up_proj.weight": "pytorch_model-00012-of-00039.bin", + "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00012-of-00039.bin", + "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00012-of-00039.bin", + "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00012-of-00039.bin", + "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00011-of-00039.bin", + "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00039.bin", + "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00012-of-00039.bin", + "model.norm.weight": "pytorch_model-00038-of-00039.bin" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..a52c50a --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,5 @@ +{ + "bos_token": "", + "eos_token": "", + "unk_token": "" +} diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000..6c00c74 --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347 +size 499723 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..b1cdcf4 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,8 @@ +{ + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "model_max_length": 1000000000000000019884624838656, + "tokenizer_class": "LlamaTokenizer", + "unk_token": "" +}