Skip to content

Conversation

@glennko
Copy link
Member

@glennko glennko commented Nov 9, 2025

Summary

Added Qwen3-0.6B (base, LoRA, INT8, LoRA+INT8, LoRA+INT4) and performed simple tests.

Checklist

  • Tested
  • Documented

Additional Information

@MarcosRiveraMartinez
Copy link
Contributor

  • Pre-commit is not passing, did you forget to run it locally?
  • Please, update the PR title and description since you are also adding support for Claude for dataset generation. Alternatively (better option), create a separate PR for this

@glennko glennko closed this Nov 22, 2025
@glennko glennko reopened this Nov 22, 2025
- add Qwen3 SFT test
- remove AI21 API
- add Claude API
- update README.md
@glennko glennko changed the title Add Qwen3 SFT test and docs update feat: add Qwen3 SFT test, remove AI21 and add Claude APIs Nov 22, 2025
@glennko
Copy link
Member Author

glennko commented Nov 22, 2025

Fixed

"torch >= 1.9.0",
"pytorch-lightning",
"transformers>=4.53.0",
"transformers>=4.36.0",
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Why did you downgraded the Transformers version, did you face any issues?

Note: transformers>=4.51.0 is required for Qwen3. More info here: https://huggingface.co/Qwen/Qwen3-0.6B

@glennko glennko merged commit 71ef9e5 into main Nov 22, 2025
2 checks passed
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