Thanks for the feedback! Do you think a dropbox-like setup with syncing some directory would suffice? or would it need to be completely offline?
42 karma · joined June 13, 2019
I FT'd some siglip models (see here: https://huggingface.co/carsonpoole/binary-siglip-text) that should be amenable to binary quantization so I'm going to tomorrow get an inference server running with that and then hopefully do the typical MTEB benchmarks for embeddings