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

llama : fix embeddings #5796

Merged
merged 9 commits into from
Mar 4, 2024
Merged

llama : fix embeddings #5796

merged 9 commits into from
Mar 4, 2024

Commits on Mar 4, 2024

  1. llama : fix embeddings 

    ggml-ci
    @ggerganov
    ggerganov committed Mar 4, 2024
    Configuration menu
    Copy the full SHA
    d034784 View commit details
    Browse the repository at this point in the history

  2. llama : do not use KV cache for non-causal models 

    ggml-ci
    @ggerganov
    ggerganov committed Mar 4, 2024
    Configuration menu
    Copy the full SHA
    eb42596 View commit details
    Browse the repository at this point in the history

  3. embeddings : fix llama_batch_init arg

    @ggerganov
    ggerganov committed Mar 4, 2024
    Configuration menu
    Copy the full SHA
    9bbeb0f View commit details
    Browse the repository at this point in the history

  4. llama : add pooling switch

    @ggerganov
    ggerganov committed Mar 4, 2024
    Configuration menu
    Copy the full SHA
    e66da35 View commit details
    Browse the repository at this point in the history

  5. llama : distinguish token vs sequence embeddings 

    ggml-ci
    @ggerganov
    ggerganov committed Mar 4, 2024
    Configuration menu
    Copy the full SHA
    79e4eed View commit details
    Browse the repository at this point in the history

  6. llama : assert pooling tensor

    @ggerganov
    ggerganov committed Mar 4, 2024
    Configuration menu
    Copy the full SHA
    fc9af15 View commit details
    Browse the repository at this point in the history

  7. llama : simplify causal mask condition 

    ggml-ci
    @ggerganov
    ggerganov committed Mar 4, 2024
    Configuration menu
    Copy the full SHA
    c23c554 View commit details
    Browse the repository at this point in the history

  8. llama : assert input batch with pooling enabled

    @ggerganov
    ggerganov committed Mar 4, 2024
    Configuration menu
    Copy the full SHA
    1af2d06 View commit details
    Browse the repository at this point in the history

  9. readme : update API changes list

    @ggerganov
    ggerganov committed Mar 4, 2024
    Configuration menu
    Copy the full SHA
    7cafaa4 View commit details
    Browse the repository at this point in the history