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

Add Command R Plus support #6491

Merged
merged 15 commits into from
Apr 9, 2024
Merged

Add Command R Plus support #6491

merged 15 commits into from
Apr 9, 2024

Commits on Apr 4, 2024

  1. Add Command R Plus GGUF

    S authored and S committed Apr 4, 2024
    Configuration menu
    Copy the full SHA
    2efcd87 View commit details
    Browse the repository at this point in the history

  2. Add Command R Plus GGUF

    S authored and S committed Apr 4, 2024
    Configuration menu
    Copy the full SHA
    fbab984 View commit details
    Browse the repository at this point in the history

  3. Loading works up to LayerNorm2D

    S authored and S committed Apr 4, 2024
    Configuration menu
    Copy the full SHA
    e4b2e2d View commit details
    Browse the repository at this point in the history

  4. Export new tensors in 1D so they are not quantized.

    S committed Apr 4, 2024
    Configuration menu
    Copy the full SHA
    c354db7 View commit details
    Browse the repository at this point in the history

Commits on Apr 5, 2024

  1. Fix embedding layer based on Noeda's example

    S committed Apr 5, 2024
    Configuration menu
    Copy the full SHA
    553b09b View commit details
    Browse the repository at this point in the history

  2. Whitespace

    S committed Apr 5, 2024
    Configuration menu
    Copy the full SHA
    f3532ff View commit details
    Browse the repository at this point in the history

  3. Add line

    S committed Apr 5, 2024
    Configuration menu
    Copy the full SHA
    ec613b8 View commit details
    Browse the repository at this point in the history

Commits on Apr 6, 2024

  1. Fix unexpected tokens on MPS. Re-add F16 fix. ((Noeda)

    S committed Apr 6, 2024
    Configuration menu
    Copy the full SHA
    c2658c3 View commit details
    Browse the repository at this point in the history

  2. dranger003: Fix block index overflow in CUDA dequantizing.

    S committed Apr 6, 2024
    Configuration menu
    Copy the full SHA
    6745ea7 View commit details
    Browse the repository at this point in the history

  3. Reverted blocked multiplication code as it still has issues and could… 

    … affect other Llama arches
    S committed Apr 6, 2024
    Configuration menu
    Copy the full SHA
    26e8f23 View commit details
    Browse the repository at this point in the history

  4. export norms as f32

    @slaren
    slaren committed Apr 6, 2024
    Configuration menu
    Copy the full SHA
    ce9413d View commit details
    Browse the repository at this point in the history

  5. fix overflow issues during quant and other cleanup

    @slaren
    slaren committed Apr 6, 2024
    Configuration menu
    Copy the full SHA
    78819c0 View commit details
    Browse the repository at this point in the history

  6. Merge pull request #1 from slaren/cmrp-fixes 

    slaren: Cmrp fixes
    @RefractAI
    RefractAI committed Apr 6, 2024
    Configuration menu
    Copy the full SHA
    8b6577b View commit details
    Browse the repository at this point in the history

Commits on Apr 7, 2024

  1. Type convention 

    Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
    @RefractAI @ggerganov
    RefractAI and ggerganov committed Apr 7, 2024
    Configuration menu
    Copy the full SHA
    d292407 View commit details
    Browse the repository at this point in the history

Commits on Apr 8, 2024

  1. dranger003: Fix more int overflow during quant.

    S committed Apr 8, 2024
    Configuration menu
    Copy the full SHA
    ea1aeba View commit details
    Browse the repository at this point in the history