Closed fugaprascolinas closed 11 months ago
@fugaprascolinas We have support for number of sentance transformers models. You can quickly try them like this:
deepctl infer \
-m 'sentence-transformers/all-MiniLM-L12-v2' \
-i 'inputs=["I like chocolate"]
Here is a list of the models we have right now: https://stage.deepinfra.com/models?type=embeddings If you want any of the models on hugging face we can easily add them https://huggingface.co/models?pipeline_tag=sentence-similarity&sort=downloads
If you want to deploy your own custom model let me know, we are working on support for this, should be out soon.
@fugaprascolinas let me know if this helper. I would like to close this issue.
This library runs the basis for different vector databases and depends in gpu for speed and stability. I am running it in Ec2 using only cpu, but the results are bad.