Sparse Changes
#2
by
maxcodefaster
- opened
Hi,
very interesting to see, that you also have mainly the sparse embedding use case. I was thinking about using this model https://huggingface.co/altaidevorg/bge-m3-distill-8l as it is probably cheaper to run in production and was wondering what exact changes did you make to just get the sparse embeddings with the inference endpoint?
Thank you in advance