Skip to content

Conversation

@aaron-lii
Copy link

  1. 根据flow推理代码对训练时的forward部分进行了修正。
  2. 根据example.py中的示例,增加了llm训练时instruct_token的拼接,与推理结构保持一致。

改动在单卡训练上已跑通。

@aaron-lii aaron-lii mentioned this pull request Dec 18, 2025
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