Skip to content

LoRa and diff with bitsandbytes #281

Open
@RonanKMcGovern

Description

  1. What changes would I need to make for GPTQ to support LoRa for Llama 2?
  2. What's the main difference between GPTQ vs bitsandbytes? Is it that GPTQ re-adjusts the weights to keep the same loss function shape?

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions