Closed deadbits closed 10 months ago
Fastembed lets you run quantized models for embeddings. With this we could avoid the pytorch requirement for sentence transformers, and just use fastembed for all the same models.
https://github.com/qdrant/fastembed
Limited on which models can be used; skipping for now
Fastembed lets you run quantized models for embeddings. With this we could avoid the pytorch requirement for sentence transformers, and just use fastembed for all the same models.
https://github.com/qdrant/fastembed