Spaces:

ggml-org

/

gguf-my-repo

like 896

Running on A10G

We should always use convert-hf-to-gguf.py since it supports most huggingface models

https://github.com/ggerganov/llama.cpp/pull/7430 will prefer to merge after this one merges

Hi @mofosyne @Galunid - I've merged a seperate PR: https://huggingface.co/spaces/ggml-org/gguf-my-repo/discussions/73 (since it was more cleaner way of doing it.

Thanks for the PR!