commit 832702f7b5691762f8520fdee86535d24ec67312 Author: ModelHub XC Date: Mon May 11 10:40:39 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: bofenghuang/vigogne-2-13b-instruct 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/.gitignore b/.gitignore new file mode 100644 index 0000000..dbb871c --- /dev/null +++ b/.gitignore @@ -0,0 +1,3 @@ +checkpoint-*/ + +tmp* \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..fff0b92 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +language: +- fr +pipeline_tag: text-generation +library_name: transformers +inference: false +tags: +- LLM +- llama +- llama-2 +--- + +

+Vigogne +

+ +# Vigogne-2-13B-Instruct: A Llama-2 based French instruction-following model + +Vigogne-2-13B-Instruct is a model based on [LLaMA-2-13B](https://ai.meta.com/llama) that has been fine-tuned to follow French instructions. + +For more information, please visit the Github repo: https://github.com/bofenghuang/vigogne + +**Usage and License Notices**: Vigogne-2-13B-Instruct follows the same usage policy as Llama-2, which can be found [here](https://ai.meta.com/llama/use-policy). + +## Usage + +```python +import torch +from transformers import AutoModelForCausalLM, AutoTokenizer, GenerationConfig +from vigogne.preprocess import generate_instruct_prompt + +model_name_or_path = "bofenghuang/vigogne-2-13b-instruct" +tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, padding_side="right", use_fast=False) +model = AutoModelForCausalLM.from_pretrained(model_name_or_path, torch_dtype=torch.float16, device_map="auto") + +user_query = "Expliquez la différence entre DoS et phishing." +prompt = generate_instruct_prompt(user_query) +input_ids = tokenizer(prompt, return_tensors="pt")["input_ids"].to(model.device) +input_length = input_ids.shape[1] + +generated_outputs = model.generate( + input_ids=input_ids, + generation_config=GenerationConfig( + temperature=0.1, + do_sample=True, + repetition_penalty=1.0, + max_new_tokens=512, + ), + return_dict_in_generate=True, +) +generated_tokens = generated_outputs.sequences[0, input_length:] +generated_text = tokenizer.decode(generated_tokens, skip_special_tokens=True) +print(generated_text) +``` + +You can also infer this model by using the following Google Colab Notebook. + +Open In Colab + +## Example Outputs + +*todo* + +## Limitations + +Vigogne is still under development, and there are many limitations that have to be addressed. Please note that it is possible that the model generates harmful or biased content, incorrect information or generally unhelpful answers. diff --git a/config.json b/config.json new file mode 100644 index 0000000..b074da1 --- /dev/null +++ b/config.json @@ -0,0 +1,26 @@ +{ + "_name_or_path": "meta-llama/Llama-2-13b-hf", + "architectures": [ + "LlamaForCausalLM" + ], + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 5120, + "initializer_range": 0.02, + "intermediate_size": 13824, + "max_position_embeddings": 4096, + "model_type": "llama", + "num_attention_heads": 40, + "num_hidden_layers": 40, + "num_key_value_heads": 40, + "pad_token_id": 0, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "tie_word_embeddings": false, + "torch_dtype": "float16", + "transformers_version": "4.32.0.dev0", + "use_cache": true, + "vocab_size": 32000 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..2e8949b --- /dev/null +++ b/generation_config.json @@ -0,0 +1,9 @@ +{ + "bos_token_id": 1, + "eos_token_id": 2, + "max_length": 4096, + "pad_token_id": 0, + "temperature": 0.9, + "top_p": 0.6, + "transformers_version": "4.32.0.dev0" +} diff --git a/model-00001-of-00014.safetensors b/model-00001-of-00014.safetensors new file mode 100644 index 0000000..c6bba45 --- /dev/null +++ b/model-00001-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6fd05769296b91018e80e100043f3345f5f3c3cc60f39ec80e5b31afcfad579 +size 1947773640 diff --git a/model-00002-of-00014.safetensors b/model-00002-of-00014.safetensors new file mode 100644 index 0000000..f3b8de7 --- /dev/null +++ b/model-00002-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a288a1c40451d56b77b0f296b8c4e637392c6f5d6e1b226636900f666cbee78 +size 1903229976 diff --git a/model-00003-of-00014.safetensors b/model-00003-of-00014.safetensors new file mode 100644 index 0000000..9bd35b5 --- /dev/null +++ b/model-00003-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd5b26a0d1717d815f3e42a697dc096db9a76686ffdf233f155d49fde3e7c4c0 +size 1903229976 diff --git a/model-00004-of-00014.safetensors b/model-00004-of-00014.safetensors new file mode 100644 index 0000000..6e552c0 --- /dev/null +++ b/model-00004-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4932a045f3cfa3633a07d3f493d09db2cfdfb55f782cf931056739966a01c84 +size 1903229992 diff --git a/model-00005-of-00014.safetensors b/model-00005-of-00014.safetensors new file mode 100644 index 0000000..40064b7 --- /dev/null +++ b/model-00005-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:083d7e071149c507e6769b4fc67dcf76629c98c5a9805a90f77b6c987f2f4351 +size 1903230008 diff --git a/model-00006-of-00014.safetensors b/model-00006-of-00014.safetensors new file mode 100644 index 0000000..af18d94 --- /dev/null +++ b/model-00006-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24a5980bed17002a7079c1432b1a6cb83aa7450efa37374d43e91b95a8d48587 +size 1903230008 diff --git a/model-00007-of-00014.safetensors b/model-00007-of-00014.safetensors new file mode 100644 index 0000000..4b53bc0 --- /dev/null +++ b/model-00007-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3264c2f163088f89be4f25dc90b8bf12c6f85aaba024ef8430e39dcfa29131f7 +size 1903230008 diff --git a/model-00008-of-00014.safetensors b/model-00008-of-00014.safetensors new file mode 100644 index 0000000..5bea458 --- /dev/null +++ b/model-00008-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd85f3ed1d12008c260c2e6a2be6728f931939b68a13ca47d0a96bd7a4407ba7 +size 1903230008 diff --git a/model-00009-of-00014.safetensors b/model-00009-of-00014.safetensors new file mode 100644 index 0000000..e576cbd --- /dev/null +++ b/model-00009-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:181d8d7137f0b2f19567eddffd97a9bb149b457acfebba9ac28a6c9443f6974b +size 1903230008 diff --git a/model-00010-of-00014.safetensors b/model-00010-of-00014.safetensors new file mode 100644 index 0000000..c8bdbd4 --- /dev/null +++ b/model-00010-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f29326070dc20dce625abb70d77e0d359c7b12863e8a78067b3f7bf0765e7de +size 1903230008 diff --git a/model-00011-of-00014.safetensors b/model-00011-of-00014.safetensors new file mode 100644 index 0000000..a60cb1b --- /dev/null +++ b/model-00011-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c852236c9c82cd80a582b8c7ab01f729178e13aba1134c315b9b6c1fea2e406 +size 1903230008 diff --git a/model-00012-of-00014.safetensors b/model-00012-of-00014.safetensors new file mode 100644 index 0000000..883761c --- /dev/null +++ b/model-00012-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf53c9fb45e82e8bdf1a95edeb1c426b422ed6ccd526e18c644f5e7b8453a16d +size 1903230008 diff --git a/model-00013-of-00014.safetensors b/model-00013-of-00014.safetensors new file mode 100644 index 0000000..1100811 --- /dev/null +++ b/model-00013-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:549ebf102e2e8a89d391c2f1acad9bc46c5d124c8963cef36eb2dc6f210e99b5 +size 1903230008 diff --git a/model-00014-of-00014.safetensors b/model-00014-of-00014.safetensors new file mode 100644 index 0000000..0e8dec8 --- /dev/null +++ b/model-00014-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f4b094dcfebe4c3d322da9ddd5b6def6425a21525f896c430b946048406a82d +size 1245236904 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..5c097b4 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,370 @@ +{ + "metadata": { + "total_size": 26031728640 + }, + "weight_map": { + "lm_head.weight": "model-00014-of-00014.safetensors", + "model.embed_tokens.weight": "model-00001-of-00014.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00014.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00014.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00014.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00014.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.10.input_layernorm.weight": "model-00004-of-00014.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.11.input_layernorm.weight": "model-00005-of-00014.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.12.input_layernorm.weight": "model-00005-of-00014.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.13.input_layernorm.weight": "model-00005-of-00014.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.14.input_layernorm.weight": "model-00006-of-00014.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.15.input_layernorm.weight": "model-00006-of-00014.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.16.input_layernorm.weight": "model-00006-of-00014.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.17.input_layernorm.weight": "model-00007-of-00014.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.18.input_layernorm.weight": "model-00007-of-00014.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.19.input_layernorm.weight": "model-00007-of-00014.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.2.input_layernorm.weight": "model-00002-of-00014.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.20.input_layernorm.weight": "model-00008-of-00014.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.21.input_layernorm.weight": "model-00008-of-00014.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.22.input_layernorm.weight": "model-00008-of-00014.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.23.input_layernorm.weight": "model-00009-of-00014.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.24.input_layernorm.weight": "model-00009-of-00014.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.25.input_layernorm.weight": "model-00009-of-00014.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.26.input_layernorm.weight": "model-00010-of-00014.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.27.input_layernorm.weight": "model-00010-of-00014.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.28.input_layernorm.weight": "model-00010-of-00014.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.29.input_layernorm.weight": "model-00011-of-00014.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.3.input_layernorm.weight": "model-00002-of-00014.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.30.input_layernorm.weight": "model-00011-of-00014.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.31.input_layernorm.weight": "model-00011-of-00014.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.32.input_layernorm.weight": "model-00012-of-00014.safetensors", + "model.layers.32.mlp.down_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.32.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.32.mlp.up_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.33.input_layernorm.weight": "model-00012-of-00014.safetensors", + "model.layers.33.mlp.down_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.33.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.33.mlp.up_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.34.input_layernorm.weight": "model-00012-of-00014.safetensors", + "model.layers.34.mlp.down_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.34.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.34.mlp.up_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", + "model.layers.34.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.34.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.34.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.35.input_layernorm.weight": "model-00013-of-00014.safetensors", + "model.layers.35.mlp.down_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.35.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.35.mlp.up_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", + "model.layers.35.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.35.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.35.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.36.input_layernorm.weight": "model-00013-of-00014.safetensors", + "model.layers.36.mlp.down_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.36.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.36.mlp.up_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.36.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", + "model.layers.36.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.36.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.36.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.36.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.37.input_layernorm.weight": "model-00013-of-00014.safetensors", + "model.layers.37.mlp.down_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.37.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.37.mlp.up_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.37.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", + "model.layers.37.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.37.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.37.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.37.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.38.input_layernorm.weight": "model-00014-of-00014.safetensors", + "model.layers.38.mlp.down_proj.weight": "model-00014-of-00014.safetensors", + "model.layers.38.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.38.mlp.up_proj.weight": "model-00014-of-00014.safetensors", + "model.layers.38.post_attention_layernorm.weight": "model-00014-of-00014.safetensors", + "model.layers.38.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.38.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.38.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.38.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.39.input_layernorm.weight": "model-00014-of-00014.safetensors", + "model.layers.39.mlp.down_proj.weight": "model-00014-of-00014.safetensors", + "model.layers.39.mlp.gate_proj.weight": "model-00014-of-00014.safetensors", + "model.layers.39.mlp.up_proj.weight": "model-00014-of-00014.safetensors", + "model.layers.39.post_attention_layernorm.weight": "model-00014-of-00014.safetensors", + "model.layers.39.self_attn.k_proj.weight": "model-00014-of-00014.safetensors", + "model.layers.39.self_attn.o_proj.weight": "model-00014-of-00014.safetensors", + "model.layers.39.self_attn.q_proj.weight": "model-00014-of-00014.safetensors", + "model.layers.39.self_attn.v_proj.weight": "model-00014-of-00014.safetensors", + "model.layers.4.input_layernorm.weight": "model-00002-of-00014.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.5.input_layernorm.weight": "model-00003-of-00014.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.6.input_layernorm.weight": "model-00003-of-00014.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.7.input_layernorm.weight": "model-00003-of-00014.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.8.input_layernorm.weight": "model-00004-of-00014.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.9.input_layernorm.weight": "model-00004-of-00014.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", + "model.norm.weight": "model-00014-of-00014.safetensors" + } +} diff --git a/pytorch_model-00001-of-00014.bin b/pytorch_model-00001-of-00014.bin new file mode 100644 index 0000000..3773ec1 --- /dev/null +++ b/pytorch_model-00001-of-00014.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42ef4903a026241831b8e77927cc8769f846945179a7cbc332e993044641a6c9 +size 1947780725 diff --git a/pytorch_model-00002-of-00014.bin b/pytorch_model-00002-of-00014.bin new file mode 100644 index 0000000..b20895d --- /dev/null +++ b/pytorch_model-00002-of-00014.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1699f542cf38eb6fbd76495dbad3505a3e5652c87a1cd1e63aabf1de551841e +size 1903237675 diff --git a/pytorch_model-00003-of-00014.bin b/pytorch_model-00003-of-00014.bin new file mode 100644 index 0000000..22265eb --- /dev/null +++ b/pytorch_model-00003-of-00014.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8eac9e924df59601c4da1e175432372a9e7e8006ecf566751660f90f91a66ff4 +size 1903237675 diff --git a/pytorch_model-00004-of-00014.bin b/pytorch_model-00004-of-00014.bin new file mode 100644 index 0000000..4c51de8 --- /dev/null +++ b/pytorch_model-00004-of-00014.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee9a8c9f9a57c49276a7cc85c55fe097b9b5c1b44b33c5031de6c6f739712ddf +size 1903237675 diff --git a/pytorch_model-00005-of-00014.bin b/pytorch_model-00005-of-00014.bin new file mode 100644 index 0000000..1bcb455 --- /dev/null +++ b/pytorch_model-00005-of-00014.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e1d25a6a258d9f05efb9652d878fd2e6ec5e6925fdf59148ba69c701d08fa89 +size 1903237675 diff --git a/pytorch_model-00006-of-00014.bin b/pytorch_model-00006-of-00014.bin new file mode 100644 index 0000000..f60621e --- /dev/null +++ b/pytorch_model-00006-of-00014.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52b8786978116ecaff08c4912360f95ee76ecbdd60188fa7b81da8117565df9c +size 1903237675 diff --git a/pytorch_model-00007-of-00014.bin b/pytorch_model-00007-of-00014.bin new file mode 100644 index 0000000..14f2e0e --- /dev/null +++ b/pytorch_model-00007-of-00014.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c6e516f2d4971d5bca2b24d812f68047f22cbea63d95dbdfae762552308a9e6 +size 1903237675 diff --git a/pytorch_model-00008-of-00014.bin b/pytorch_model-00008-of-00014.bin new file mode 100644 index 0000000..2b94390 --- /dev/null +++ b/pytorch_model-00008-of-00014.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae846c4b8291740589bd8be14b14142bfc0bb1a5bf810b1391fc7147e7cdb3dc +size 1903237675 diff --git a/pytorch_model-00009-of-00014.bin b/pytorch_model-00009-of-00014.bin new file mode 100644 index 0000000..530b973 --- /dev/null +++ b/pytorch_model-00009-of-00014.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a3bba226d7b6dbafda32f4b3886ad2b95eb2caba96660608d369722b3e88acd +size 1903237675 diff --git a/pytorch_model-00010-of-00014.bin b/pytorch_model-00010-of-00014.bin new file mode 100644 index 0000000..c2fb977 --- /dev/null +++ b/pytorch_model-00010-of-00014.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0944fb6bb2e1eb5cde4245f9b946f1f6f931a9a6b6b382fa2a858fecd40b90af +size 1903237675 diff --git a/pytorch_model-00011-of-00014.bin b/pytorch_model-00011-of-00014.bin new file mode 100644 index 0000000..c818b77 --- /dev/null +++ b/pytorch_model-00011-of-00014.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0da2c8f5f8bab9fc8a8ae17cd1453b86629a2c18d6b6a24c215f8c54d02ea2f4 +size 1903237675 diff --git a/pytorch_model-00012-of-00014.bin b/pytorch_model-00012-of-00014.bin new file mode 100644 index 0000000..48dc2eb --- /dev/null +++ b/pytorch_model-00012-of-00014.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4437080b5dbacf2ad71b53927c91a8cc8d997a5e7cf031b079aaed784ae05de +size 1903237675 diff --git a/pytorch_model-00013-of-00014.bin b/pytorch_model-00013-of-00014.bin new file mode 100644 index 0000000..59c2416 --- /dev/null +++ b/pytorch_model-00013-of-00014.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8700c136427ad5aa8922a93941b5c9f3099dcd7e3b6bca0c408a9cb1214af501 +size 1903237675 diff --git a/pytorch_model-00014-of-00014.bin b/pytorch_model-00014-of-00014.bin new file mode 100644 index 0000000..eb4eb50 --- /dev/null +++ b/pytorch_model-00014-of-00014.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25322b38c7448f93f6f679115abe74a00c8cb56b42578235b603ec41c70dd934 +size 1245241071 diff --git a/pytorch_model.bin.index.json b/pytorch_model.bin.index.json new file mode 100644 index 0000000..6abd7bd --- /dev/null +++ b/pytorch_model.bin.index.json @@ -0,0 +1,410 @@ +{ + "metadata": { + "total_size": 26031738880 + }, + "weight_map": { + "lm_head.weight": "pytorch_model-00014-of-00014.bin", + "model.embed_tokens.weight": "pytorch_model-00001-of-00014.bin", + "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00014.bin", + "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00014.bin", + "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00014.bin", + "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00014.bin", + "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00014.bin", + "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00014.bin", + "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00014.bin", + "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00014.bin", + "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00014.bin", + "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00014.bin", + "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00014.bin", + "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00014.bin", + "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00014.bin", + "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00014.bin", + "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00014.bin", + "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00014.bin", + "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00014.bin", + "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00014.bin", + "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00014.bin", + "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00014.bin", + "model.layers.10.input_layernorm.weight": "pytorch_model-00004-of-00014.bin", + "model.layers.10.mlp.down_proj.weight": "pytorch_model-00004-of-00014.bin", + "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00004-of-00014.bin", + "model.layers.10.mlp.up_proj.weight": "pytorch_model-00004-of-00014.bin", + "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00004-of-00014.bin", + "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00004-of-00014.bin", + "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00004-of-00014.bin", + "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00004-of-00014.bin", + "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00014.bin", + "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00004-of-00014.bin", + "model.layers.11.input_layernorm.weight": "pytorch_model-00005-of-00014.bin", + "model.layers.11.mlp.down_proj.weight": "pytorch_model-00005-of-00014.bin", + "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00004-of-00014.bin", + "model.layers.11.mlp.up_proj.weight": "pytorch_model-00005-of-00014.bin", + "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00005-of-00014.bin", + "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00004-of-00014.bin", + "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00004-of-00014.bin", + "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00004-of-00014.bin", + "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00014.bin", + "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00004-of-00014.bin", + "model.layers.12.input_layernorm.weight": "pytorch_model-00005-of-00014.bin", + "model.layers.12.mlp.down_proj.weight": "pytorch_model-00005-of-00014.bin", + "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00005-of-00014.bin", + "model.layers.12.mlp.up_proj.weight": "pytorch_model-00005-of-00014.bin", + "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00005-of-00014.bin", + "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00005-of-00014.bin", + "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00005-of-00014.bin", + "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00005-of-00014.bin", + "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00014.bin", + "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00005-of-00014.bin", + "model.layers.13.input_layernorm.weight": "pytorch_model-00005-of-00014.bin", + "model.layers.13.mlp.down_proj.weight": "pytorch_model-00005-of-00014.bin", + "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00005-of-00014.bin", + "model.layers.13.mlp.up_proj.weight": "pytorch_model-00005-of-00014.bin", + "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00005-of-00014.bin", + "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00005-of-00014.bin", + "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00005-of-00014.bin", + "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00005-of-00014.bin", + "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00014.bin", + "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00005-of-00014.bin", + "model.layers.14.input_layernorm.weight": "pytorch_model-00006-of-00014.bin", + "model.layers.14.mlp.down_proj.weight": "pytorch_model-00006-of-00014.bin", + "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00005-of-00014.bin", + "model.layers.14.mlp.up_proj.weight": "pytorch_model-00006-of-00014.bin", + "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00006-of-00014.bin", + "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00005-of-00014.bin", + "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00005-of-00014.bin", + "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00005-of-00014.bin", + "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00014.bin", + "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00005-of-00014.bin", + "model.layers.15.input_layernorm.weight": "pytorch_model-00006-of-00014.bin", + "model.layers.15.mlp.down_proj.weight": "pytorch_model-00006-of-00014.bin", + "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00006-of-00014.bin", + "model.layers.15.mlp.up_proj.weight": "pytorch_model-00006-of-00014.bin", + "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00006-of-00014.bin", + "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00006-of-00014.bin", + "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00006-of-00014.bin", + "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00006-of-00014.bin", + "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00014.bin", + "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00006-of-00014.bin", + "model.layers.16.input_layernorm.weight": "pytorch_model-00006-of-00014.bin", + "model.layers.16.mlp.down_proj.weight": "pytorch_model-00006-of-00014.bin", + "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00006-of-00014.bin", + "model.layers.16.mlp.up_proj.weight": "pytorch_model-00006-of-00014.bin", + "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00006-of-00014.bin", + "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00006-of-00014.bin", + "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00006-of-00014.bin", + "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00006-of-00014.bin", + "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00014.bin", + "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00006-of-00014.bin", + "model.layers.17.input_layernorm.weight": "pytorch_model-00007-of-00014.bin", + "model.layers.17.mlp.down_proj.weight": "pytorch_model-00007-of-00014.bin", + "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00006-of-00014.bin", + "model.layers.17.mlp.up_proj.weight": "pytorch_model-00007-of-00014.bin", + "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00007-of-00014.bin", + "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00006-of-00014.bin", + "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00006-of-00014.bin", + "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00006-of-00014.bin", + "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00014.bin", + "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00006-of-00014.bin", + "model.layers.18.input_layernorm.weight": "pytorch_model-00007-of-00014.bin", + "model.layers.18.mlp.down_proj.weight": "pytorch_model-00007-of-00014.bin", + "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00007-of-00014.bin", + "model.layers.18.mlp.up_proj.weight": "pytorch_model-00007-of-00014.bin", + "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00007-of-00014.bin", + "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00007-of-00014.bin", + "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00007-of-00014.bin", + "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00007-of-00014.bin", + "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00014.bin", + "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00007-of-00014.bin", + "model.layers.19.input_layernorm.weight": "pytorch_model-00007-of-00014.bin", + "model.layers.19.mlp.down_proj.weight": "pytorch_model-00007-of-00014.bin", + "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00007-of-00014.bin", + "model.layers.19.mlp.up_proj.weight": "pytorch_model-00007-of-00014.bin", + "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00007-of-00014.bin", + "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00007-of-00014.bin", + "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00007-of-00014.bin", + "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00007-of-00014.bin", + "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00014.bin", + "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00007-of-00014.bin", + "model.layers.2.input_layernorm.weight": "pytorch_model-00002-of-00014.bin", + "model.layers.2.mlp.down_proj.weight": "pytorch_model-00002-of-00014.bin", + "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00014.bin", + "model.layers.2.mlp.up_proj.weight": "pytorch_model-00002-of-00014.bin", + "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00002-of-00014.bin", + "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00014.bin", + "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00014.bin", + "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00014.bin", + "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00014.bin", + "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00014.bin", + "model.layers.20.input_layernorm.weight": "pytorch_model-00008-of-00014.bin", + "model.layers.20.mlp.down_proj.weight": "pytorch_model-00008-of-00014.bin", + "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00007-of-00014.bin", + "model.layers.20.mlp.up_proj.weight": "pytorch_model-00008-of-00014.bin", + "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00008-of-00014.bin", + "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00007-of-00014.bin", + "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00007-of-00014.bin", + "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00007-of-00014.bin", + "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00014.bin", + "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00007-of-00014.bin", + "model.layers.21.input_layernorm.weight": "pytorch_model-00008-of-00014.bin", + "model.layers.21.mlp.down_proj.weight": "pytorch_model-00008-of-00014.bin", + "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00008-of-00014.bin", + "model.layers.21.mlp.up_proj.weight": "pytorch_model-00008-of-00014.bin", + "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00008-of-00014.bin", + "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00008-of-00014.bin", + "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00008-of-00014.bin", + "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00008-of-00014.bin", + "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00014.bin", + "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00008-of-00014.bin", + "model.layers.22.input_layernorm.weight": "pytorch_model-00008-of-00014.bin", + "model.layers.22.mlp.down_proj.weight": "pytorch_model-00008-of-00014.bin", + "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00008-of-00014.bin", + "model.layers.22.mlp.up_proj.weight": "pytorch_model-00008-of-00014.bin", + "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00008-of-00014.bin", + "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00008-of-00014.bin", + "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00008-of-00014.bin", + "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00008-of-00014.bin", + "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00014.bin", + "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00008-of-00014.bin", + "model.layers.23.input_layernorm.weight": "pytorch_model-00009-of-00014.bin", + "model.layers.23.mlp.down_proj.weight": "pytorch_model-00009-of-00014.bin", + "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00008-of-00014.bin", + "model.layers.23.mlp.up_proj.weight": "pytorch_model-00009-of-00014.bin", + "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00009-of-00014.bin", + "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00008-of-00014.bin", + "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00008-of-00014.bin", + "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00008-of-00014.bin", + "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00014.bin", + "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00008-of-00014.bin", + "model.layers.24.input_layernorm.weight": "pytorch_model-00009-of-00014.bin", + "model.layers.24.mlp.down_proj.weight": "pytorch_model-00009-of-00014.bin", + "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00009-of-00014.bin", + "model.layers.24.mlp.up_proj.weight": "pytorch_model-00009-of-00014.bin", + "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00009-of-00014.bin", + "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00009-of-00014.bin", + "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00009-of-00014.bin", + "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00009-of-00014.bin", + "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00014.bin", + "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00009-of-00014.bin", + "model.layers.25.input_layernorm.weight": "pytorch_model-00009-of-00014.bin", + "model.layers.25.mlp.down_proj.weight": "pytorch_model-00009-of-00014.bin", + "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00009-of-00014.bin", + "model.layers.25.mlp.up_proj.weight": "pytorch_model-00009-of-00014.bin", + "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00009-of-00014.bin", + "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00009-of-00014.bin", + "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00009-of-00014.bin", + "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00009-of-00014.bin", + "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00014.bin", + "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00009-of-00014.bin", + "model.layers.26.input_layernorm.weight": "pytorch_model-00010-of-00014.bin", + "model.layers.26.mlp.down_proj.weight": "pytorch_model-00010-of-00014.bin", + "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00009-of-00014.bin", + "model.layers.26.mlp.up_proj.weight": "pytorch_model-00010-of-00014.bin", + "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00010-of-00014.bin", + "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00009-of-00014.bin", + "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00009-of-00014.bin", + "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00009-of-00014.bin", + "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00014.bin", + "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00009-of-00014.bin", + "model.layers.27.input_layernorm.weight": "pytorch_model-00010-of-00014.bin", + "model.layers.27.mlp.down_proj.weight": "pytorch_model-00010-of-00014.bin", + "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00010-of-00014.bin", + "model.layers.27.mlp.up_proj.weight": "pytorch_model-00010-of-00014.bin", + "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00010-of-00014.bin", + "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00010-of-00014.bin", + "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00010-of-00014.bin", + "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00010-of-00014.bin", + "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00014.bin", + "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00010-of-00014.bin", + "model.layers.28.input_layernorm.weight": "pytorch_model-00010-of-00014.bin", + "model.layers.28.mlp.down_proj.weight": "pytorch_model-00010-of-00014.bin", + "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00010-of-00014.bin", + "model.layers.28.mlp.up_proj.weight": "pytorch_model-00010-of-00014.bin", + "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00010-of-00014.bin", + "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00010-of-00014.bin", + "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00010-of-00014.bin", + "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00010-of-00014.bin", + "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00014.bin", + "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00010-of-00014.bin", + "model.layers.29.input_layernorm.weight": "pytorch_model-00011-of-00014.bin", + "model.layers.29.mlp.down_proj.weight": "pytorch_model-00011-of-00014.bin", + "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00010-of-00014.bin", + "model.layers.29.mlp.up_proj.weight": "pytorch_model-00011-of-00014.bin", + "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00011-of-00014.bin", + "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00010-of-00014.bin", + "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00010-of-00014.bin", + "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00010-of-00014.bin", + "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00014.bin", + "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00010-of-00014.bin", + "model.layers.3.input_layernorm.weight": "pytorch_model-00002-of-00014.bin", + "model.layers.3.mlp.down_proj.weight": "pytorch_model-00002-of-00014.bin", + "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00002-of-00014.bin", + "model.layers.3.mlp.up_proj.weight": "pytorch_model-00002-of-00014.bin", + "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00002-of-00014.bin", + "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00002-of-00014.bin", + "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00002-of-00014.bin", + "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00002-of-00014.bin", + "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00014.bin", + "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00002-of-00014.bin", + "model.layers.30.input_layernorm.weight": "pytorch_model-00011-of-00014.bin", + "model.layers.30.mlp.down_proj.weight": "pytorch_model-00011-of-00014.bin", + "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00011-of-00014.bin", + "model.layers.30.mlp.up_proj.weight": "pytorch_model-00011-of-00014.bin", + "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00011-of-00014.bin", + "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00011-of-00014.bin", + "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00011-of-00014.bin", + "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00011-of-00014.bin", + "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00014.bin", + "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00011-of-00014.bin", + "model.layers.31.input_layernorm.weight": "pytorch_model-00011-of-00014.bin", + "model.layers.31.mlp.down_proj.weight": "pytorch_model-00011-of-00014.bin", + "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00011-of-00014.bin", + "model.layers.31.mlp.up_proj.weight": "pytorch_model-00011-of-00014.bin", + "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00011-of-00014.bin", + "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00011-of-00014.bin", + "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00011-of-00014.bin", + "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00011-of-00014.bin", + "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00014.bin", + "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00011-of-00014.bin", + "model.layers.32.input_layernorm.weight": "pytorch_model-00012-of-00014.bin", + "model.layers.32.mlp.down_proj.weight": "pytorch_model-00012-of-00014.bin", + "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00011-of-00014.bin", + "model.layers.32.mlp.up_proj.weight": "pytorch_model-00012-of-00014.bin", + "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00012-of-00014.bin", + "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00011-of-00014.bin", + "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00011-of-00014.bin", + "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00011-of-00014.bin", + "model.layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00014.bin", + "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00011-of-00014.bin", + "model.layers.33.input_layernorm.weight": "pytorch_model-00012-of-00014.bin", + "model.layers.33.mlp.down_proj.weight": "pytorch_model-00012-of-00014.bin", + "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00012-of-00014.bin", + "model.layers.33.mlp.up_proj.weight": "pytorch_model-00012-of-00014.bin", + "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00012-of-00014.bin", + "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00012-of-00014.bin", + "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00012-of-00014.bin", + "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00012-of-00014.bin", + "model.layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00014.bin", + "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00012-of-00014.bin", + "model.layers.34.input_layernorm.weight": "pytorch_model-00012-of-00014.bin", + "model.layers.34.mlp.down_proj.weight": "pytorch_model-00012-of-00014.bin", + "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00012-of-00014.bin", + "model.layers.34.mlp.up_proj.weight": "pytorch_model-00012-of-00014.bin", + "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00012-of-00014.bin", + "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00012-of-00014.bin", + "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00012-of-00014.bin", + "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00012-of-00014.bin", + "model.layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00014.bin", + "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00012-of-00014.bin", + "model.layers.35.input_layernorm.weight": "pytorch_model-00013-of-00014.bin", + "model.layers.35.mlp.down_proj.weight": "pytorch_model-00013-of-00014.bin", + "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00012-of-00014.bin", + "model.layers.35.mlp.up_proj.weight": "pytorch_model-00013-of-00014.bin", + "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00013-of-00014.bin", + "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00012-of-00014.bin", + "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00012-of-00014.bin", + "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00012-of-00014.bin", + "model.layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00014.bin", + "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00012-of-00014.bin", + "model.layers.36.input_layernorm.weight": "pytorch_model-00013-of-00014.bin", + "model.layers.36.mlp.down_proj.weight": "pytorch_model-00013-of-00014.bin", + "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00013-of-00014.bin", + "model.layers.36.mlp.up_proj.weight": "pytorch_model-00013-of-00014.bin", + "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00013-of-00014.bin", + "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00013-of-00014.bin", + "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00013-of-00014.bin", + "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00013-of-00014.bin", + "model.layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00014.bin", + "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00013-of-00014.bin", + "model.layers.37.input_layernorm.weight": "pytorch_model-00013-of-00014.bin", + "model.layers.37.mlp.down_proj.weight": "pytorch_model-00013-of-00014.bin", + "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00013-of-00014.bin", + "model.layers.37.mlp.up_proj.weight": "pytorch_model-00013-of-00014.bin", + "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00013-of-00014.bin", + "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00013-of-00014.bin", + "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00013-of-00014.bin", + "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00013-of-00014.bin", + "model.layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00014.bin", + "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00013-of-00014.bin", + "model.layers.38.input_layernorm.weight": "pytorch_model-00014-of-00014.bin", + "model.layers.38.mlp.down_proj.weight": "pytorch_model-00014-of-00014.bin", + "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00013-of-00014.bin", + "model.layers.38.mlp.up_proj.weight": "pytorch_model-00014-of-00014.bin", + "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00014-of-00014.bin", + "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00013-of-00014.bin", + "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00013-of-00014.bin", + "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00013-of-00014.bin", + "model.layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00014.bin", + "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00013-of-00014.bin", + "model.layers.39.input_layernorm.weight": "pytorch_model-00014-of-00014.bin", + "model.layers.39.mlp.down_proj.weight": "pytorch_model-00014-of-00014.bin", + "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00014-of-00014.bin", + "model.layers.39.mlp.up_proj.weight": "pytorch_model-00014-of-00014.bin", + "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00014-of-00014.bin", + "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00014-of-00014.bin", + "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00014-of-00014.bin", + "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00014-of-00014.bin", + "model.layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-00014-of-00014.bin", + "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00014-of-00014.bin", + "model.layers.4.input_layernorm.weight": "pytorch_model-00002-of-00014.bin", + "model.layers.4.mlp.down_proj.weight": "pytorch_model-00002-of-00014.bin", + "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00002-of-00014.bin", + "model.layers.4.mlp.up_proj.weight": "pytorch_model-00002-of-00014.bin", + "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00002-of-00014.bin", + "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00002-of-00014.bin", + "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00002-of-00014.bin", + "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00002-of-00014.bin", + "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00014.bin", + "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00002-of-00014.bin", + "model.layers.5.input_layernorm.weight": "pytorch_model-00003-of-00014.bin", + "model.layers.5.mlp.down_proj.weight": "pytorch_model-00003-of-00014.bin", + "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00002-of-00014.bin", + "model.layers.5.mlp.up_proj.weight": "pytorch_model-00003-of-00014.bin", + "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00003-of-00014.bin", + "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00002-of-00014.bin", + "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00002-of-00014.bin", + "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00002-of-00014.bin", + "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00014.bin", + "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00002-of-00014.bin", + "model.layers.6.input_layernorm.weight": "pytorch_model-00003-of-00014.bin", + "model.layers.6.mlp.down_proj.weight": "pytorch_model-00003-of-00014.bin", + "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00003-of-00014.bin", + "model.layers.6.mlp.up_proj.weight": "pytorch_model-00003-of-00014.bin", + "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00003-of-00014.bin", + "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00003-of-00014.bin", + "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00003-of-00014.bin", + "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00003-of-00014.bin", + "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00014.bin", + "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00003-of-00014.bin", + "model.layers.7.input_layernorm.weight": "pytorch_model-00003-of-00014.bin", + "model.layers.7.mlp.down_proj.weight": "pytorch_model-00003-of-00014.bin", + "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00003-of-00014.bin", + "model.layers.7.mlp.up_proj.weight": "pytorch_model-00003-of-00014.bin", + "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00003-of-00014.bin", + "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00003-of-00014.bin", + "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00003-of-00014.bin", + "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00003-of-00014.bin", + "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00014.bin", + "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00003-of-00014.bin", + "model.layers.8.input_layernorm.weight": "pytorch_model-00004-of-00014.bin", + "model.layers.8.mlp.down_proj.weight": "pytorch_model-00004-of-00014.bin", + "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00003-of-00014.bin", + "model.layers.8.mlp.up_proj.weight": "pytorch_model-00004-of-00014.bin", + "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00004-of-00014.bin", + "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00003-of-00014.bin", + "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00003-of-00014.bin", + "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00003-of-00014.bin", + "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00014.bin", + "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00003-of-00014.bin", + "model.layers.9.input_layernorm.weight": "pytorch_model-00004-of-00014.bin", + "model.layers.9.mlp.down_proj.weight": "pytorch_model-00004-of-00014.bin", + "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00004-of-00014.bin", + "model.layers.9.mlp.up_proj.weight": "pytorch_model-00004-of-00014.bin", + "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00004-of-00014.bin", + "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00004-of-00014.bin", + "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00004-of-00014.bin", + "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00004-of-00014.bin", + "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00014.bin", + "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00004-of-00014.bin", + "model.norm.weight": "pytorch_model-00014-of-00014.bin" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..451134b --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} 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..2ef41cb --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,35 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "bos_token": { + "__type": "AddedToken", + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "clean_up_tokenization_spaces": false, + "eos_token": { + "__type": "AddedToken", + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "legacy": false, + "model_max_length": 1000000000000000019884624838656, + "pad_token": null, + "padding_side": "right", + "sp_model_kwargs": {}, + "tokenizer_class": "LlamaTokenizer", + "unk_token": { + "__type": "AddedToken", + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/vigogne_logo.png b/vigogne_logo.png new file mode 100644 index 0000000..9cb4674 Binary files /dev/null and b/vigogne_logo.png differ