Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[Fix] remove the speaker embedding in the llm inputs during instruct fine-tuning #444

Open
wants to merge 1 commit into
base: main
Choose a base branch
from

Conversation

Shengqiang-Li
Copy link

@Shengqiang-Li Shengqiang-Li commented Sep 27, 2024

  1. 问题:在训练阶段,LLM输入序列中有speaker embedding。在指令微调模型推理时LLM输入序列没有speaker embedding。因此对于指令微调模型而言,训练和推理存在mismatch,效果不理想。
  2. 解决方案:LLM增加instruct_finetuning的参数,缺省值为False。当该参数为True时,训练阶段也会去掉LLM输入序列中的speaker embedding,从而保证指令微调模型可以正常训练和推理。

@Shengqiang-Li Shengqiang-Li changed the title remove the speaker embedding in the llm inputs during instruct fine-tuning [Fix] remove the speaker embedding in the llm inputs during instruct fine-tuning Sep 27, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant