Ollama compatability

#13
by twine-network - opened

Is it possible to make a GGUF version of this model to use with Ollama? I haven't been able to find a tool or workflow for this. Wondering if it is even possible.

Not sure if ollama supports colbert-style models?

Ollama docs:

Coming soon
More features are coming to support workflows that involve embeddings:

    Batch embeddings: processing multiple input data prompts simultaneously
    OpenAI API Compatibility: support for the /v1/embeddings OpenAI-compatible endpoint
    More embedding model architectures: support for ColBERT, RoBERTa, and other embedding model architectures

Added colbert support here: https://github.com/michaelfeil/infinity

Oh nice. I had just come across your infinity project a few days ago and had it sitting in an open tab to look at when I got a minute. That just got bumped up the todo list. Thanks

Sign up or log in to comment