Github：https://github.com/CrazyBoyM/llama3-Chinese-chat
放出训练配方细节供网友参考分享：
DPO(beta 0.5) + lora rank128, alpha256 + 打开"lm_head", "input_layernorm", "post_attention_layernorm", "norm"层训练。
偏好中文和emoji表情，且不损伤原instruct版模型能力。
Git下载
#Git模型下载
git clone https://www.modelscope.cn/baicai003/Llama3-Chinese-instruct-DPO-beta0.5.git
- Downloads last month
- 0
Unable to determine this model’s pipeline type. Check the
docs
.