Edit model card

Llama3-Chinese-Chat-emoji

在原模型shenzhi-wang/Llama3-70B-Chinese-Chat的基础上使用shareAI/DPO-zh-en-emoji进行QLoRA微调而来, 希望能重现原版llama3喜欢小表情的习惯

失败惹, 原模型emoji能力已经被抑制惹, DPO也调不出来惹(悲)

新模型指路Orion-zhen/Llama3-70B-Orion-Chinese👈

Downloads last month
9
Safetensors
Model size
70.6B params
Tensor type
BF16
·
Inference API
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Dataset used to train Orion-zhen/Llama3-Chinese-Chat-emoji