Prerequisites

• I am running the latest code. Mention the version if possible as well.
• I carefully followed the README.md.
• I searched using keywords relevant to my issue to make sure that I am creating a new issue that is not already open (or closed).
• I reviewed the Discussions, and have a new and useful enhancement to share.

Feature Description

llama-cli -hf ... always check for tag <==> gguf mapping and etag header each time it runs, which currently make it impossible to be used offline

Motivation

I usually work on train, having ability to use -hf while being offline can be nice

Possible Implementation

common_params_handle_model need to be updated in such a way that:

• common_get_hf_file response can be cached
• common_download_model can be allow to fail if the local file already exist