commit e5dee38e2cf3690cb216f4bf5099036ffa2676b5 Author: ModelHub XC Date: Fri May 29 22:57:56 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: bofenghuang/vigogne-7b-instruct Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c7d9f33 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,34 @@ +*.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 +*.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..f11bfd2 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +license: openrail +language: +- fr +pipeline_tag: text-generation +library_name: transformers +tags: +- llama +- LLM +inference: false +--- + +

+Vigogne +

+ +# Vigogne-7B-Instruct: A French Instruction-following LLaMA Model + +Vigogne-7B-Instruct is a LLaMA-7B model fine-tuned to follow the French instructions. + +For more information, please visit the Github repo: https://github.com/bofenghuang/vigogne + +**Usage and License Notices**: Same as [Stanford Alpaca](https://github.com/tatsu-lab/stanford_alpaca), Vigogne is intended and licensed for research use only. The dataset is CC BY NC 4.0 (allowing only non-commercial use) and models trained using the dataset should not be used outside of research purposes. + +## Changelog + +All versions are available in branches. + +- **V1.0**: Initial release, trained on the translated Stanford Alpaca dataset. +- **V1.1**: Improved translation quality of the Stanford Alpaca dataset. +- **V2.0**: Expanded training dataset to 224k for better performance. +- **V3.0**: Further expanded training dataset to 262k for improved results. + +## Usage + +```python +import torch +from transformers import AutoModelForCausalLM, AutoTokenizer, GenerationConfig +from vigogne.preprocess import generate_instruct_prompt + +model_name_or_path = "bofenghuang/vigogne-7b-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 + +## 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..2e960d3 --- /dev/null +++ b/config.json @@ -0,0 +1,24 @@ +{ + "_name_or_path": "huggyllama/llama-7b", + "architectures": [ + "LlamaForCausalLM" + ], + "bos_token_id": 1, + "eos_token_id": 2, + "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": 0, + "rms_norm_eps": 1e-06, + "tie_word_embeddings": false, + "torch_dtype": "float16", + "transformers_version": "4.28.1", + "use_cache": true, + "vocab_size": 32000 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..1372199 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,7 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "pad_token_id": 0, + "transformers_version": "4.28.1" +} diff --git a/pytorch_model-00001-of-00007.bin b/pytorch_model-00001-of-00007.bin new file mode 100644 index 0000000..d6f85c7 --- /dev/null +++ b/pytorch_model-00001-of-00007.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2bfef594dcd26b6809f545f0a12176f148fe84760e6392a4a55fc5a4ba7fcc44 +size 1981889895 diff --git a/pytorch_model-00002-of-00007.bin b/pytorch_model-00002-of-00007.bin new file mode 100644 index 0000000..0456d5c --- /dev/null +++ b/pytorch_model-00002-of-00007.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b252f0e9c398338cec8d713ada9e257953b40c6a94ad483be573fa1c9f893a7 +size 1990296833 diff --git a/pytorch_model-00003-of-00007.bin b/pytorch_model-00003-of-00007.bin new file mode 100644 index 0000000..eea385d --- /dev/null +++ b/pytorch_model-00003-of-00007.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47016b32e7fc86a55c096dca035df078a8bcba430b99ea719685d207ea0bec7f +size 1990296833 diff --git a/pytorch_model-00004-of-00007.bin b/pytorch_model-00004-of-00007.bin new file mode 100644 index 0000000..459ee53 --- /dev/null +++ b/pytorch_model-00004-of-00007.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae7f80c55935baa6351b44141c80d3d7ae11438d2fa95cfe35fd0bd7528d4eb2 +size 1990296897 diff --git a/pytorch_model-00005-of-00007.bin b/pytorch_model-00005-of-00007.bin new file mode 100644 index 0000000..9a5b70f --- /dev/null +++ b/pytorch_model-00005-of-00007.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93687760f09685edf617fcc2ca3d869300e9b2f07fc7bc5c0005963e1735e8f6 +size 1933656733 diff --git a/pytorch_model-00006-of-00007.bin b/pytorch_model-00006-of-00007.bin new file mode 100644 index 0000000..09dae70 --- /dev/null +++ b/pytorch_model-00006-of-00007.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a355be18f4ba4066cfb984c1ae7d7b5ad4c0346ef63522d7b0fd99825b47a38 +size 1933673793 diff --git a/pytorch_model-00007-of-00007.bin b/pytorch_model-00007-of-00007.bin new file mode 100644 index 0000000..ffacc30 --- /dev/null +++ b/pytorch_model-00007-of-00007.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c359d4516ee80b3299d3ff628cafff316c08cf1dcff7e1b7cc2cf52f1e43345 +size 1656836567 diff --git a/pytorch_model.bin.index.json b/pytorch_model.bin.index.json new file mode 100644 index 0000000..6e8526d --- /dev/null +++ b/pytorch_model.bin.index.json @@ -0,0 +1,330 @@ +{ + "metadata": { + "total_size": 13476839424 + }, + "weight_map": { + "lm_head.weight": "pytorch_model-00007-of-00007.bin", + "model.embed_tokens.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin", + "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin", + "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.10.input_layernorm.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.10.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.10.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin", + "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.11.input_layernorm.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.11.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.11.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin", + "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.12.input_layernorm.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.12.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.12.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin", + "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.13.input_layernorm.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.13.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.13.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin", + "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.14.input_layernorm.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.14.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.14.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin", + "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.15.input_layernorm.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.15.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.15.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin", + "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.16.input_layernorm.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.16.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.16.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin", + "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.17.input_layernorm.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.17.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.17.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin", + "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.18.input_layernorm.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.18.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.18.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin", + "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.19.input_layernorm.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.19.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.19.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin", + "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin", + "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.20.input_layernorm.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.20.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.20.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin", + "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.21.input_layernorm.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.21.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.21.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin", + "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.22.input_layernorm.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.22.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.22.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin", + "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.23.input_layernorm.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.23.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.23.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin", + "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.24.input_layernorm.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.24.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.24.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin", + "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.25.input_layernorm.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.25.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.25.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin", + "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.26.input_layernorm.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.26.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.26.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin", + "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.27.input_layernorm.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.27.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.27.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin", + "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.28.input_layernorm.weight": "pytorch_model-00007-of-00007.bin", + "model.layers.28.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin", + "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.28.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin", + "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin", + "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin", + "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.29.input_layernorm.weight": "pytorch_model-00007-of-00007.bin", + "model.layers.29.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin", + "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin", + "model.layers.29.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin", + "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin", + "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin", + "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin", + "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin", + "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00007.bin", + "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin", + "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin", + "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.30.input_layernorm.weight": "pytorch_model-00007-of-00007.bin", + "model.layers.30.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin", + "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin", + "model.layers.30.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin", + "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin", + "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin", + "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin", + "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin", + "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00007.bin", + "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin", + "model.layers.31.input_layernorm.weight": "pytorch_model-00007-of-00007.bin", + "model.layers.31.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin", + "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin", + "model.layers.31.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin", + "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin", + "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin", + "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin", + "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin", + "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00007.bin", + "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin", + "model.layers.4.input_layernorm.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.4.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.4.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin", + "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.5.input_layernorm.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.5.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.5.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin", + "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.6.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin", + "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin", + "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin", + "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.9.input_layernorm.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.9.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.9.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin", + "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.norm.weight": "pytorch_model-00007-of-00007.bin" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..d85ba6c --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "", + "lstrip": false, + "normalized": true, + "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..5ab645d --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,34 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "bos_token": { + "__type": "AddedToken", + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "clean_up_tokenization_spaces": false, + "eos_token": { + "__type": "AddedToken", + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "model_max_length": 2048, + "pad_token": null, + "padding_side": "right", + "sp_model_kwargs": {}, + "tokenizer_class": "LlamaTokenizer", + "unk_token": { + "__type": "AddedToken", + "content": "", + "lstrip": false, + "normalized": true, + "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