Skip to content

feat: add local Qwen3-Omni API and fine-tune regression#318

Open
glennko wants to merge 5 commits intomainfrom
glenn/qwen3omni
Open

feat: add local Qwen3-Omni API and fine-tune regression#318
glennko wants to merge 5 commits intomainfrom
glenn/qwen3omni

Conversation

@glennko
Copy link
Member

@glennko glennko commented Feb 5, 2026

  • swap Qwen3-Omni dataset generation to load Hugging Face checkpoints locally and wire up tests/ docs
  • ensure AGENTS.md/CLAUDE.md stay untracked
  • add a lightweight GPT-2 fine-tuning test that asserts weights actually change

Summary

Checklist

  • Tested
  • Documented

Additional Information

* swap Qwen3-Omni dataset generation to load Hugging Face checkpoints locally and wire up tests/
  docs
  * ensure AGENTS.md/CLAUDE.md stay untracked
  * add a lightweight GPT-2 fine-tuning test that asserts weights actually change
self.tokenizer = AutoTokenizer.from_pretrained(
model_name_or_path, trust_remote_code=True, **tokenizer_kwargs
)
self.model = AutoModelForCausalLM.from_pretrained(
Copy link
Contributor

Choose a reason for hiding this comment

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

It doesn't look correct. I don't think AutoModelForCausalLM is supported for this model. Just try AutoModelForMultimodalLM

Copy link
Member Author

Choose a reason for hiding this comment

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

I've made the suggested changes.

chore: apply autoflake/isort fixes

style: apply black formatting
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.

2 participants