Skip to content

Conversation

@JamesTheZ
Copy link

Thanks for the great work!

This PR supports more models of LLaMA/Qwen2/Mistral. It also supports the model who has attention_bias (e.g., Qwen2.5 models).

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