commit a38a0b2c912998e837edda95e26677a3291a1a3f Author: ModelHub XC Date: Mon Apr 20 03:36:01 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: MaybeOK/vicuna-7b-v1.5-16k Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7bc225d --- /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 +*.bin.* filter=lfs diff=lfs merge=lfs -text +*.bz2 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 +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack 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 +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar 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 +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..5191c08 --- /dev/null +++ b/README.md @@ -0,0 +1,50 @@ +--- +inference: false +license: llama2 +--- + +# Vicuna Model Card + +This model is copied from the coordinating repo of https://huggingface.co/lmsys/vicuna-7b-v1.5-16k + +## Model Details + +Vicuna is a chat assistant trained by fine-tuning Llama 2 on user-shared conversations collected from ShareGPT. + +- **Developed by:** [LMSYS](https://lmsys.org/) +- **Model type:** An auto-regressive language model based on the transformer architecture +- **License:** Llama 2 Community License Agreement +- **Finetuned from model:** [Llama 2](https://arxiv.org/abs/2307.09288) + +### Model Sources + +- **Repository:** https://github.com/lm-sys/FastChat +- **Blog:** https://lmsys.org/blog/2023-03-30-vicuna/ +- **Paper:** https://arxiv.org/abs/2306.05685 +- **Demo:** https://chat.lmsys.org/ + +## Uses + +The primary use of Vicuna is research on large language models and chatbots. +The primary intended users of the model are researchers and hobbyists in natural language processing, machine learning, and artificial intelligence. + +## How to Get Started with the Model + +- Command line interface: https://github.com/lm-sys/FastChat#vicuna-weights +- APIs (OpenAI API, Huggingface API): https://github.com/lm-sys/FastChat/tree/main#api + +## Training Details + +Vicuna v1.5 (16k) is fine-tuned from Llama 2 with supervised instruction fine-tuning and linear RoPE scaling. +The training data is around 125K conversations collected from ShareGPT.com. These conversations are packed into sequences that contain 16K tokens each. +See more details in the "Training Details of Vicuna Models" section in the appendix of this [paper](https://arxiv.org/pdf/2306.05685.pdf). + +## Evaluation + +![Evaluation Results](https://github.com/lm-sys/lm-sys.github.io/blob/main/public/images/webdata/vicuna_v1.5_eval.png?raw=true) + +Vicuna is evaluated with standard benchmarks, human preference, and LLM-as-a-judge. See more details in this [paper](https://arxiv.org/pdf/2306.05685.pdf) and [leaderboard](https://huggingface.co/spaces/lmsys/chatbot-arena-leaderboard). + +## Difference between different versions of Vicuna + +See [vicuna_weights_version.md](https://github.com/lm-sys/FastChat/blob/main/docs/vicuna_weights_version.md) \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..f9d93cf --- /dev/null +++ b/config.json @@ -0,0 +1,30 @@ +{ + "_name_or_path": "vicuna-7b-v1.5-16k", + "architectures": [ + "LlamaForCausalLM" + ], + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 11008, + "max_sequence_length": 16384, + "max_position_embeddings": 4096, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 32, + "pad_token_id": 0, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 4.0, + "type": "linear" + }, + "tie_word_embeddings": false, + "torch_dtype": "float16", + "transformers_version": "4.31.0", + "use_cache": true, + "vocab_size": 32000 +} diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..9fbcf95 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"task":"text-generation"} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..95ccc84 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,9 @@ +{ + "bos_token_id": 1, + "eos_token_id": 2, + "max_length": 16384, + "pad_token_id": 0, + "temperature": 0.9, + "top_p": 0.6, + "transformers_version": "4.31.0" +} diff --git a/pytorch_model-00001-of-00002.bin b/pytorch_model-00001-of-00002.bin new file mode 100644 index 0000000..71bc931 --- /dev/null +++ b/pytorch_model-00001-of-00002.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a41f9924b9433362e61846e2d2ed579e0c1180491145cdaf4bf3579333bdb208 +size 9976634558 diff --git a/pytorch_model-00002-of-00002.bin b/pytorch_model-00002-of-00002.bin new file mode 100644 index 0000000..b3a0601 --- /dev/null +++ b/pytorch_model-00002-of-00002.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0ab7db90a3d5fa32b17c09e1ddbd1224e5144c71187aefff0e1fef55d0771dd +size 3500315539 diff --git a/pytorch_model.bin.index.json b/pytorch_model.bin.index.json new file mode 100644 index 0000000..3056e5c --- /dev/null +++ b/pytorch_model.bin.index.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aca3c1facc89d12311a667c32e85ac86e625990992ea8a189e3b036ba371b931 +size 26788 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..14761dc --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,24 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "", + "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..0e6bb25 --- /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": 16384, + "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 + } +}