Skip to content

[Feature Request] Support for TEQ #84

@shauryr

Description

@shauryr

As mentioned in this paper - TEQ: Trainable Equivalent Transformation for Quantization of LLMs.
The authors of this paper are claiming - "The training process is lightweight, requiring only 1K steps and less than 1‰ of the original model’s trainable parameters."

Is this in the pipeline? It would be great if unsloth can support this.

https://arxiv.org/pdf/2310.10944.pdf

https://github.com/intel/neural-compressor

Thank you for building this awesome library!

Metadata

Metadata

Assignees

No one assigned

    Labels

    feature requestFeature request pending on roadmap

    Type

    No type
    No fields configured for issues without a type.

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions