使用代码下载开源的大模型文件示例以及中文微调llama资源汇总:

一、下载示例 

from huggingface_hub import snapshot_download

repo_id = "THUDM/chatglm2-6b"
local_dir = './chatglm2-6b/'
cache_dir = local_dir + "/cache"
while True:
    try:
        snapshot_download(cache_dir=cache_dir,
        local_dir=local_dir,
        repo_id=repo_id,
        local_dir_use_symlinks=False, # 不转为缓存乱码的形式, auto, Small files (<5MB) are duplicated in `local_dir` while a symlink is created for bigger files.
        resume_download=True,
        allow_patterns=["*.model", "*.json", "*.bin",
        "*.py", "*.md", "*.txt"],
        ignore_patterns=["*.safetensors", "*.msgpack",
        "*.h5", "*.ot", ],
        )
    except Exception as e :
        print(e)

二、资源汇总

  1. Chinese Llama 2 7B 链接:LinkSoul/Chinese-Llama-2-7b · Hugging Face

  2. OpenBuddy-LLaMA2-13B 链接:OpenBuddy/openbuddy-llama2-13b-v8.1-fp16 · Hugging Face

  3. firefly-llama2-13b 链接:GitHub - yangjianxin1/Firefly: Firefly(流萤): 中文对话式大语言模型(全量微调+QLoRA),支持微调Llma2、Llama、Qwen、Baichuan、ChatGLM2、InternLM、Ziya、Bloom等大模型

  4. YaYi-7B-Llama2、YaYi-13B-Llama2
    链接:wenge-research/yayi-13b-llama2 · Hugging Face

  5. 伶荔Chinese-LLaMA-2-7B和13B 链接:GitHub - CVI-SZU/Linly: Chinese-LLaMA 1&2、Chinese-Falcon 基础模型;ChatFlow中文对话模型;中文OpenLLaMA模型;NLP预训练/指令微调数据集

  6. Llama2-Chinese 链接:GitHub - ymcui/Chinese-LLaMA-Alpaca-2: 中文 LLaMA-2 & Alpaca-2 大模型二期项目 (Chinese LLaMA-2 & Alpaca-2 LLMs) 链接:ziqingyang/chinese-llama-2-7b · Hugging Face

  7. Chinese-LLaMA2-7b from LinkSoul 链接:GitHub - LinkSoul-AI/Chinese-Llama-2-7b: 开源社区第一个能下载、能运行的中文 LLaMA2 模型!

  8. Llama2-Chinese-7B from FlagAlpha 链接:GitHub - FlagAlpha/Llama2-Chinese: Llama中文社区,最好的中文Llama大模型,完全开源可商用

  9. YaYi from Wenge 链接:GitHub - wenge-research/YaYi: 雅意大模型:为客户打造安全可靠的专属大模型,基于大规模中英文多领域指令数据训练的 LlaMA 2 & BLOOM 系列模型,由中科闻歌算法团队研发。(Repo for YaYi Chinese LLMs based on LlaMA2 & BLOOM)

你可能感兴趣的:(NLP,机器学习)