Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Fix: modelloader handling of model_kwargs load_in*bit #1999

Merged
merged 10 commits into from
Oct 30, 2024
Merged

Fix: modelloader handling of model_kwargs load_in*bit #1999

merged 10 commits into from
Oct 30, 2024

Commits on Oct 30, 2024

  1. fix: load_in_*bit not properly read

    @NanoCode012 @winglian
    NanoCode012 authored and winglian committed Oct 30, 2024
    Configuration menu
    Copy the full SHA
    10925d6 View commit details
    Browse the repository at this point in the history

  2. fix: load_*bit check

    @NanoCode012 @winglian
    NanoCode012 authored and winglian committed Oct 30, 2024
    Configuration menu
    Copy the full SHA
    163e02d View commit details
    Browse the repository at this point in the history

  3. fix: typo

    @NanoCode012 @winglian
    NanoCode012 authored and winglian committed Oct 30, 2024
    Configuration menu
    Copy the full SHA
    0d91e54 View commit details
    Browse the repository at this point in the history

  4. refactor: load * bit handling

    @NanoCode012 @winglian
    NanoCode012 authored and winglian committed Oct 30, 2024
    Configuration menu
    Copy the full SHA
    2de1df4 View commit details
    Browse the repository at this point in the history

  5. feat: add test dpo lora multi-gpu

    @NanoCode012 @winglian
    NanoCode012 authored and winglian committed Oct 30, 2024
    Configuration menu
    Copy the full SHA
    d5f4641 View commit details
    Browse the repository at this point in the history

  6. fix: turn off sample packing for dpo

    @NanoCode012 @winglian
    NanoCode012 authored and winglian committed Oct 30, 2024
    Configuration menu
    Copy the full SHA
    f761ff2 View commit details
    Browse the repository at this point in the history

  7. fix: missing warmup_steps

    @NanoCode012 @winglian
    NanoCode012 authored and winglian committed Oct 30, 2024
    Configuration menu
    Copy the full SHA
    b80aaf5 View commit details
    Browse the repository at this point in the history

  8. fix: test to load in 8bit for lora

    @NanoCode012 @winglian
    NanoCode012 authored and winglian committed Oct 30, 2024
    Configuration menu
    Copy the full SHA
    3eaec39 View commit details
    Browse the repository at this point in the history

  9. skip 8bit lora on h100, add 4bit lora on h100 to multi gpu tests

    @winglian
    winglian committed Oct 30, 2024
    Configuration menu
    Copy the full SHA
    bd23847 View commit details
    Browse the repository at this point in the history

  10. chore: reduce max_steps

    @NanoCode012 @winglian
    NanoCode012 authored and winglian committed Oct 30, 2024
    Configuration menu
    Copy the full SHA
    fc0cb6a View commit details
    Browse the repository at this point in the history