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

btlm and falcon monkey patches for flash attn #566

Merged
merged 6 commits into from
Sep 17, 2023
Merged

btlm and falcon monkey patches for flash attn #566

merged 6 commits into from
Sep 17, 2023

Commits on Sep 15, 2023

  1. btlm and falcon monkey patches for flash attn

    @winglian
    winglian committed Sep 15, 2023
    Configuration menu
    Copy the full SHA
    82eda69 View commit details
    Browse the repository at this point in the history

  2. fix var

    @winglian
    winglian committed Sep 15, 2023
    Configuration menu
    Copy the full SHA
    79b3fe5 View commit details
    Browse the repository at this point in the history

  3. improve checks for various falcon model sizes

    @winglian
    winglian committed Sep 15, 2023
    Configuration menu
    Copy the full SHA
    f512bda View commit details
    Browse the repository at this point in the history

  4. scale the attn based on the configuration settings

    @winglian
    winglian committed Sep 15, 2023
    Configuration menu
    Copy the full SHA
    0b04d83 View commit details
    Browse the repository at this point in the history

Commits on Sep 16, 2023

  1. make sure modeling remote code is available first, leave lm_head alone

    @winglian
    winglian committed Sep 16, 2023
    Configuration menu
    Copy the full SHA
    4b5cca1 View commit details
    Browse the repository at this point in the history

  2. tweak imports for tests

    @winglian
    winglian committed Sep 16, 2023
    Configuration menu
    Copy the full SHA
    9233ecc View commit details
    Browse the repository at this point in the history