feat: GGUF transformer embedder shows “use in llama.cpp” button for create_chat_completion, not create_embeddings

[davidberenstein1957]

Additionally, it might be interesting to consider adding GGUFed version of more models?

[davidberenstein1957]

@Vaibhavs10

[julien-c]

Additionally, it might be interesting to consider adding GGUFed version of more models?

wdym?

[davidberenstein1957]

Additionally, it might be interesting to consider adding GGUFed version of more models?

wdym?

Most sentence-transformer models don’t have a GGUFed version but we could create a bot that loops over them and creates a PR to add the GGUFed version.

The code is already there so we could potentially schedule through a CRON or do this once to set a standard for the current sentence-transformers on the Hub.

[julien-c]

hmm, automated PRs tend to not work as well as user-initiated conversion, so far at least

Maybe start by promoting to users that they can very easily convert those models to GGUF into a new repo?