Update the GGUF usage with llama.cpp doc page

[julien-c]

there's now way cleaner syntax than https://huggingface.co/docs/hub/en/gguf-llamacpp to load a model from HF in llama.cpp

[cakiki]

This is resolved by #1280 right?

[julien-c]

hmm no only partly i think

https://huggingface.co/docs/hub/en/gguf-llamacpp is still sub-optimal imo.

cc @Vaibhavs10, and also cc @ngxson who opened huggingface/huggingface.js#778 which is the same command(s) but "in-product" (on the Hub) vs. in a doc

[Vaibhavs10]

Good catch, will open a PR today to update and ask for everyone's reviews! 👍

[Vaibhavs10]

Opened a PR to discuss: #1326

cc: @ngxson - I wasn't able to add you as a reviewer, but please feel free to review

[cakiki]

@julien-c now it can be closed I guess 😺

[julien-c]

yes we can close but @Vaibhavs10 @ngxson i would still add how to install (recommend brew etc) to that doc page WDYT?

Closing in the meantime