LoRA微调 glaive-function-calling-v2-sharegpt 数据集,需要多大参数量的模型能有较好的训练效果? #4908
Unanswered
chenkuncloud
asked this question in
Q&A
Replies: 1 comment 3 replies
-
参考作者在知乎的文章单卡 3 小时训练专属大模型 Agent:基于 LLaMA Factory 实战 |
Beta Was this translation helpful? Give feedback.
3 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
数据集:hiyouga/glaive-function-calling-v2-sharegpt
对于Qwen2系列而言,求问0.5B/1.5B/7B哪个更适合拿来做微调,完成 Function Call 的任务?超参数大概如何设置(轮数、学习率、总批大小)?是否还需要搭配其他的数据集?
Beta Was this translation helpful? Give feedback.
All reactions