Skip to content

R1 distill qwen#316

Merged
musab-mk merged 33 commits intomainfrom
r1_distill_qwen
Apr 16, 2025
Merged

R1 distill qwen#316
musab-mk merged 33 commits intomainfrom
r1_distill_qwen

Conversation

@khai-meetkai
Copy link
Collaborator

  • Add prompt templates for Qwen2.5, distilled Deepskeek, and R1

@khai-meetkai khai-meetkai marked this pull request as draft April 16, 2025 02:39
@khai-meetkai khai-meetkai requested a review from musab-mk April 16, 2025 08:28
@khai-meetkai khai-meetkai marked this pull request as ready for review April 16, 2025 08:28
@musab-mk musab-mk merged commit aa3dbdd into main Apr 16, 2025
3 checks passed
@musab-mk musab-mk deleted the r1_distill_qwen branch April 16, 2025 19:34
@neonsecret
Copy link

neonsecret commented Apr 20, 2025

Why is think token not expected in the templates? Isn't the CoT the point of using r1?

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.

3 participants