777K 1 year ago

Embedding models on very large sentence level datasets.

embedding 22m 33m

1 year ago

4f5da3bd944d · 67MB

bert
·
33.2M
·
F16
Apache License Version 2.0, January 2004
{ "num_ctx": 256 }

Readme

Note: this model requires Ollama 0.1.26 or later. Download it here. It can only be used to generate embeddings.

The project aims to train sentence embedding models on very large sentence level datasets using a self-supervised contrastive learning objective.

Usage

REST API

curl http://localhost:11434/api/embeddings -d '{
  "model": "all-minilm",
  "prompt": "The sky is blue because of Rayleigh scattering"
}'

Python library

ollama.embeddings(model='all-minilm', prompt='The sky is blue because of Rayleigh scattering')

Javascript library

ollama.embeddings({ model: 'all-minilm', prompt: 'The sky is blue because of Rayleigh scattering' })

References

HuggingFace

Website