Skip to content

[Feature Request] Add support for Nanbeige4-3B-Base model #9761

Description

@andru196

Reminder

  • I have read the above rules and searched the existing issues.

Description

I would like to request support for fine-tuning Nanbeige4-3B-Base, a recently released state-of-the-art 3B parameter model from Nanbeige LLM Lab that demonstrates exceptional reasoning and coding capabilities.
Motivation
Exceptional Performance on Reasoning Benchmarks
Nanbeige4-3B-Base outperforms models with up to 10× more parameters.
Full Transformers Compatibility

Available on HuggingFace:
https://huggingface.co/Nanbeige/Nanbeige4-3B-Base

Pull Request

No response

Metadata

Metadata

Assignees

No one assigned

    Labels

    enhancementNew feature or requestpendingThis problem is yet to be addressed

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions