GGUF by ggerganov · Pull Request #2398 · ggerganov/llama.cpp
github.com
ref: ggerganov/ggml#302 WIP in progress Current plan: implement GGUF import in ggml add sample code to write / read dummy GGUF files refactor convert.py + export GGUF remove quantized data su...

Been a lot of good work done the past week by several pivotal members, and now the boss is back and focused on it, going to be a very breaking change but I’m really excited where this will lead us!

    • noneabove1182OPMEnglish
      3·
      1 year ago

      it’s a standardizing of a universal GGML format which would mean going forward no more breaking changes when new formats are worked on, and also includes the same functionality of llama.cpp for all GGML types (falcon, mpt, starcoder etc)

      • KerfuffleEnglish
        2·
        1 year ago

        which would mean going forward no more breaking changes when new formats are worked on

        I definitely wouldn’t count on that.

        But it does make it much easier to do some changes, like adding/changing model specific fields which previously would have required a format change. Stuff like changing or dropping support for existing quantizations would also break stuff independent of the model format itself.

        • noneabove1182OPMEnglish
          2·
          1 year ago

          oh yeah definitely didn’t mean “no more breaking changes”, just that we’ve had several from ggml file format changes, and so THAT portion of the breaking is going away