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

GGUF #122

Merged
merged 16 commits into from
Sep 2, 2023
Merged

GGUF #122

merged 16 commits into from
Sep 2, 2023

Commits on Aug 26, 2023

  1. Initial changes required for GGUF support

    @martindevans
    martindevans committed Aug 26, 2023
    Configuration menu
    Copy the full SHA
    2056078 View commit details
    Browse the repository at this point in the history

  2. Removed LLAMA_MAX_DEVICES (not used)

    @martindevans
    martindevans committed Aug 26, 2023
    Configuration menu
    Copy the full SHA
    6ffa28f View commit details
    Browse the repository at this point in the history

  3. Passing ctx to llama_token_nl(_ctx)

    @martindevans
    martindevans committed Aug 26, 2023
    Configuration menu
    Copy the full SHA
    0c98ae1 View commit details
    Browse the repository at this point in the history

  4. Rewritten TokenToSpan/TokenToString to better fit the new way it's do… 

    …ne in llama.cpp with a few different options:

 - Just convert it to a `string`, nice and simple
 - Write the bytes to a `Span<byte>` no allocations
 - Write the chars to a `StringBuilder` potentially no allocations
    @martindevans
    martindevans committed Aug 26, 2023
    Configuration menu
    Copy the full SHA
    31287b5 View commit details
    Browse the repository at this point in the history

  5. Switched to codellama-7b.gguf in tests (probably temporarily)

    @martindevans
    martindevans committed Aug 26, 2023
    Configuration menu
    Copy the full SHA
    95dc12d View commit details
    Browse the repository at this point in the history

Commits on Aug 27, 2023

  1. Fix Tokenize of new line, Remove space inserts

    @saddam213
    saddam213 committed Aug 27, 2023
    Configuration menu
    Copy the full SHA
    a5d742b View commit details
    Browse the repository at this point in the history

Commits on Aug 28, 2023

  1. Merge pull request #3 from saddam213/feature/gguf 

    Fix Tokenize of new line, Remove space inserts
    @martindevans
    martindevans authored Aug 28, 2023
    Configuration menu
    Copy the full SHA
    974f160 View commit details
    Browse the repository at this point in the history

  2. Added binaries generated by this action: https://github.com/SciSharp/… 

    …LLamaSharp/actions/runs/6002797872/job/16279896150

Based on this version: ggerganov/llama.cpp@6b73ef1
    @martindevans
    martindevans committed Aug 28, 2023
    Configuration menu
    Copy the full SHA
    2022b82 View commit details
    Browse the repository at this point in the history

  3. Removed hardcoded paths from projects, modified Runtime.targets to ex… 

    …clude missing binaries
    @martindevans
    martindevans committed Aug 28, 2023
    Configuration menu
    Copy the full SHA
    ba49ea2 View commit details
    Browse the repository at this point in the history

  4. Included Linux deps

    @martindevans
    martindevans committed Aug 28, 2023
    Configuration menu
    Copy the full SHA
    6711a59 View commit details
    Browse the repository at this point in the history

Commits on Aug 29, 2023

  1. Added binaries for CUDA+Linux

    @martindevans
    martindevans committed Aug 29, 2023
    Configuration menu
    Copy the full SHA
    c9d08b9 View commit details
    Browse the repository at this point in the history

  2. Updated some of the docs

    @martindevans
    martindevans committed Aug 29, 2023
    Configuration menu
    Copy the full SHA
    516c291 View commit details
    Browse the repository at this point in the history

Commits on Aug 30, 2023

  1. Changes to compile in VS Mac + change model to llama2 

    This commit includes changes to compile en VS Mac + changest to use llama2 not codellama.

It includes MacOS binaries in memory and metal
    @SignalRT
    SignalRT committed Aug 30, 2023
    Configuration menu
    Copy the full SHA
    fb007e5 View commit details
    Browse the repository at this point in the history

Commits on Aug 31, 2023

  1. Merge pull request #4 from SignalRT/GGUF-MERGE 

    Changes to compile in VS Mac + change model to llama2
    @martindevans
    martindevans authored Aug 31, 2023
    Configuration menu
    Copy the full SHA
    cb506cc View commit details
    Browse the repository at this point in the history

Commits on Sep 2, 2023

  1. Added some comments on various native methods

    @martindevans
    martindevans committed Sep 2, 2023
    Configuration menu
    Copy the full SHA
    bcf06e2 View commit details
    Browse the repository at this point in the history

  2. Merge branch 'gguf' of github.com:martindevans/LLamaSharp into gguf

    @martindevans
    martindevans committed Sep 2, 2023
    Configuration menu
    Copy the full SHA
    97349d9 View commit details
    Browse the repository at this point in the history