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 PLaMo model #3557

Merged
merged 19 commits into from
Dec 24, 2023
Merged

add PLaMo model #3557

merged 19 commits into from
Dec 24, 2023

Commits on Dec 18, 2023

  1. add plamo mock

    @okdshin
    okdshin committed Dec 18, 2023
    Configuration menu
    Copy the full SHA
    feb0966 View commit details
    Browse the repository at this point in the history

  2. add tensor loading

    @okdshin
    okdshin committed Dec 18, 2023
    Configuration menu
    Copy the full SHA
    4c585b4 View commit details
    Browse the repository at this point in the history

  3. plamo convert

    @okdshin
    okdshin committed Dec 18, 2023
    Configuration menu
    Copy the full SHA
    b2330f5 View commit details
    Browse the repository at this point in the history

  4. update norm

    @okdshin
    okdshin committed Dec 18, 2023
    Configuration menu
    Copy the full SHA
    9d49236 View commit details
    Browse the repository at this point in the history

  5. able to compile

    @okdshin
    okdshin committed Dec 18, 2023
    Configuration menu
    Copy the full SHA
    4a3ef4f View commit details
    Browse the repository at this point in the history

  6. fix norm_rms_eps hparam

    @okdshin
    okdshin committed Dec 18, 2023
    Configuration menu
    Copy the full SHA
    a22040a View commit details
    Browse the repository at this point in the history

  7. runnable

    @okdshin
    okdshin committed Dec 18, 2023
    Configuration menu
    Copy the full SHA
    86d5348 View commit details
    Browse the repository at this point in the history

  8. use inp_pos

    @okdshin
    okdshin committed Dec 18, 2023
    Configuration menu
    Copy the full SHA
    f76fd39 View commit details
    Browse the repository at this point in the history

  9. seems ok

    @okdshin
    okdshin committed Dec 18, 2023
    Configuration menu
    Copy the full SHA
    ca8f698 View commit details
    Browse the repository at this point in the history

  10. update kqv code

    @okdshin
    okdshin committed Dec 18, 2023
    Configuration menu
    Copy the full SHA
    febc635 View commit details
    Browse the repository at this point in the history

  11. remove develop code

    @okdshin
    okdshin committed Dec 18, 2023
    Configuration menu
    Copy the full SHA
    907b921 View commit details
    Browse the repository at this point in the history

  12. update README

    @okdshin
    okdshin committed Dec 18, 2023
    Configuration menu
    Copy the full SHA
    9339ffc View commit details
    Browse the repository at this point in the history

Commits on Dec 24, 2023

  1. shuffle attn_q.weight and attn_output.weight for broadcasting

    @okdshin
    okdshin committed Dec 24, 2023
    Configuration menu
    Copy the full SHA
    db1b18d View commit details
    Browse the repository at this point in the history

  2. remove plamo_llm_build_kqv and use llm_build_kqv

    @okdshin
    okdshin committed Dec 24, 2023
    Configuration menu
    Copy the full SHA
    26340a1 View commit details
    Browse the repository at this point in the history

  3. fix style

    @okdshin
    okdshin committed Dec 24, 2023
    Configuration menu
    Copy the full SHA
    700f7c6 View commit details
    Browse the repository at this point in the history

  4. Merge branch 'master' into add_pfnet_plamo_13b_2

    @okdshin
    okdshin committed Dec 24, 2023
    Configuration menu
    Copy the full SHA
    602cc71 View commit details
    Browse the repository at this point in the history

  5. update

    @okdshin
    okdshin committed Dec 24, 2023
    Configuration menu
    Copy the full SHA
    307481f View commit details
    Browse the repository at this point in the history

  6. llama : remove obsolete KQ_scale

    @ggerganov
    ggerganov committed Dec 24, 2023
    Configuration menu
    Copy the full SHA
    eedd434 View commit details
    Browse the repository at this point in the history

  7. plamo : fix tensor names for correct GPU offload

    @ggerganov
    ggerganov committed Dec 24, 2023
    Configuration menu
    Copy the full SHA
    1949c95 View commit details
    Browse the repository at this point in the history