commit 8d8481c3ac8b19249a7a6a82b78ee4c77f7fd4fd Author: ModelHub XC Date: Sat May 2 12:47:50 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: hfl/chinese-alpaca-2-7b Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..53d7257 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,47 @@ +*.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 +*.gguf* filter=lfs diff=lfs merge=lfs -text +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* 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..3d498f3 --- /dev/null +++ b/README.md @@ -0,0 +1,40 @@ +--- +license: apache-2.0 +language: +- zh +- en +--- + +# Chinese-Alpaca-2-7B + +**This is the full Chinese-Alpaca-2-7B model，which can be loaded directly for inference and full-parameter training.** + +**Related models👇** +* Long context base models + * [Chinese-LLaMA-2-7B-16K (full model)](https://huggingface.co/hfl/chinese-llama-2-7b-16k) + * [Chinese-LLaMA-2-LoRA-7B-16K (LoRA model)](https://huggingface.co/hfl/chinese-llama-2-lora-7b-16k) + * [Chinese-LLaMA-2-13B-16K (full model)](https://huggingface.co/hfl/chinese-llama-2-13b-16k) + * [Chinese-LLaMA-2-LoRA-13B-16K (LoRA model)](https://huggingface.co/hfl/chinese-llama-2-lora-13b-16k) +* Base models + * [Chinese-LLaMA-2-7B (full model)](https://huggingface.co/hfl/chinese-llama-2-7b) + * [Chinese-LLaMA-2-LoRA-7B (LoRA model)](https://huggingface.co/hfl/chinese-llama-2-lora-7b) + * [Chinese-LLaMA-2-13B (full model)](https://huggingface.co/hfl/chinese-llama-2-13b) + * [Chinese-LLaMA-2-LoRA-13B (LoRA model)](https://huggingface.co/hfl/chinese-llama-2-lora-13b) +* Instruction/Chat models + * [Chinese-Alpaca-2-7B (full model)](https://huggingface.co/hfl/chinese-alpaca-2-7b) + * [Chinese-Alpaca-2-LoRA-7B (LoRA model)](https://huggingface.co/hfl/chinese-alpaca-2-lora-7b) + * [Chinese-Alpaca-2-13B (full model)](https://huggingface.co/hfl/chinese-alpaca-2-13b) + * [Chinese-Alpaca-2-LoRA-13B (LoRA model)](https://huggingface.co/hfl/chinese-alpaca-2-lora-13b) + + +# Description of Chinese-LLaMA-Alpaca-2 +This project is based on the Llama-2, released by Meta, and it is the second generation of the Chinese LLaMA & Alpaca LLM project. We open-source Chinese LLaMA-2 (foundation model) and Alpaca-2 (instruction-following model). These models have been expanded and optimized with Chinese vocabulary beyond the original Llama-2. We used large-scale Chinese data for incremental pre-training, which further improved the fundamental semantic understanding of the Chinese language, resulting in a significant performance improvement compared to the first-generation models. The relevant models support a 4K context and can be expanded up to 18K+ using the NTK method. + +The main contents of this project include: + +* 🚀 New extended Chinese vocabulary beyond Llama-2, open-sourcing the Chinese LLaMA-2 and Alpaca-2 LLMs. +* 🚀 Open-sourced the pre-training and instruction finetuning (SFT) scripts for further tuning on user's data +* 🚀 Quickly deploy and experience the quantized LLMs on CPU/GPU of personal PC +* 🚀 Support for LLaMA ecosystems like 🤗transformers, llama.cpp, text-generation-webui, LangChain, vLLM etc. + +Please refer to [https://github.com/ymcui/Chinese-LLaMA-Alpaca-2/](https://github.com/ymcui/Chinese-LLaMA-Alpaca-2/) for details. \ No newline at end of file diff --git a/SHA256.md b/SHA256.md new file mode 100644 index 0000000..c35d80c --- /dev/null +++ b/SHA256.md @@ -0,0 +1,8 @@ +68f516b143f9cdfe669efb3ae4edd707ff6e996559a68160d9f2d900e5bf1a3a config.json +a8094d0e4f79ad03cb77120df07d86e6fcf77b9654b5ca8323ecccdb40b3d84d generation_config.json +182d552f893db16f7196afdf6ec13f05b43650985c9ce71f41f6d576e978c53f pytorch_model-00001-of-00002.bin +1f22e3d669ea912c4b0428fb4095f2068eb6192c89406ddd441de87ccec0c1b5 pytorch_model-00002-of-00002.bin +f6d0ee483ec154f789a0aa263fd9ce1dc4a85dca7cb73915bfb679b67079012b pytorch_model.bin.index.json +dfd7f38bbbe1f22c1f6e05db6241ad82176a9765d91b51b3fee3e3835e6ac75f special_tokens_map.json +a3b8844863b200dfcca971db228e96ce388290dfcf72c15d7a9d2f604bac787c tokenizer.model +305a57cf5eca7b87705ffe64d9c0ccb23ff09e85342597227ac4207953f7fea6 tokenizer_config.json diff --git a/config.json b/config.json new file mode 100644 index 0000000..494a783 --- /dev/null +++ b/config.json @@ -0,0 +1,25 @@ +{ + "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": 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": null, + "tie_word_embeddings": false, + "torch_dtype": "float16", + "transformers_version": "4.31.0", + "use_cache": true, + "vocab_size": 55296 +} \ No newline at end of file diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..de5b5ba --- /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": "4.31.0" +} \ No newline at end of file diff --git a/pytorch_model-00001-of-00002.bin b/pytorch_model-00001-of-00002.bin new file mode 100644 index 0000000..794b06e --- /dev/null +++ b/pytorch_model-00001-of-00002.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:182d552f893db16f7196afdf6ec13f05b43650985c9ce71f41f6d576e978c53f +size 10167475414 diff --git a/pytorch_model-00002-of-00002.bin b/pytorch_model-00002-of-00002.bin new file mode 100644 index 0000000..c969cd5 --- /dev/null +++ b/pytorch_model-00002-of-00002.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f22e3d669ea912c4b0428fb4095f2068eb6192c89406ddd441de87ccec0c1b5 +size 3691156371 diff --git a/pytorch_model.bin.index.json b/pytorch_model.bin.index.json new file mode 100644 index 0000000..df40688 --- /dev/null +++ b/pytorch_model.bin.index.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6d0ee483ec154f789a0aa263fd9ce1dc4a85dca7cb73915bfb679b67079012b +size 26787 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..9588650 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,24 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "pad_token": "", + "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..3df664f --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3b8844863b200dfcca971db228e96ce388290dfcf72c15d7a9d2f604bac787c +size 844403 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..5076180 --- /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": 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 + }, + "legacy": true, + "model_max_length": 1000000000000000019884624838656, + "pad_token": null, + "sp_model_kwargs": {}, + "tokenizer_class": "LlamaTokenizer", + "unk_token": { + "__type": "AddedToken", + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "use_fast": false +}