??? v3版指令模型已发布，欢迎使用 ? [HF版] [GGUF版]

Llama-3-Chinese-8B-Instruct-LoRA

这个仓库包含了Llama-3-Chinese-8B-Instruct-LoRA，它是在Llama-3-Chinese-8B的基础上，使用了500万条指令数据进行精调。

注意：LoRA必须和原版Meta-Llama-3-8B进行合并才能得到完整模型。

更多细节（性能、使用方法等）请参考GitHub项目页面：https://github.com/ymcui/Chinese-LLaMA-Alpaca-3

其他

• 完整模型：https://modelscope.cn/models/ChineseAlpacaGroup/llama-3-chinese-8b-instruct

• GGUF模型（llama.cpp兼容）：https://modelscope.cn/models/ChineseAlpacaGroup/llama-3-chinese-8b-instruct-gguf

• 关于本模型的提问，请通过 https://github.com/ymcui/Chinese-LLaMA-Alpaca-3 提交issue

This repository contains Llama-3-Chinese-8B-Instruct-LoRA, which is further tuned with 5M instruction data on Llama-3-Chinese-8B.

Note: You must combine LoRA with the original Meta-Llama-3-8B to obtain full weight.

Further details (performance, usage, etc.) should refer to GitHub project page: https://github.com/ymcui/Chinese-LLaMA-Alpaca-3

Others

• For full model, please see: https://modelscope.cn/models/ChineseAlpacaGroup/llama-3-chinese-8b-instruct

• For GGUF model (llama.cpp compatible), please see: https://modelscope.cn/models/ChineseAlpacaGroup/llama-3-chinese-8b-instruct-gguf

• If you have questions/issues regarding this model, please submit an issue through https://github.com/ymcui/Chinese-LLaMA-Alpaca-3