??? v3版指令模型已发布，欢迎使用 ? [HF版] [GGUF版]
Llama-3-Chinese-8B-Instruct-v2-LoRA
这个仓库包含了Llama-3-Chinese-8B-Instruct-v2-LoRA，它是在Meta-Llama-3-8B-Instruct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-Instruct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-v2
GGUF模型（llama.cpp兼容）：https://modelscope.cn/models/ChineseAlpacaGroup/llama-3-chinese-8b-instruct-v2-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-v2-LoRA, which is further tuned with 5M instruction data on Meta-Llama-3-8B-Instruct.
Note: You must combine LoRA with the original Meta-Llama-3-8B-Instruct 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-v2
For GGUF model (llama.cpp compatible), please see: https://modelscope.cn/models/ChineseAlpacaGroup/llama-3-chinese-8b-instruct-v2-gguf
If you have questions/issues regarding this model, please submit an issue through https://github.com/ymcui/Chinese-LLaMA-Alpaca-3
评论