[do-me]

Just quantized the models for onnx usage in e.g. transformers.js and got 4x reduced file size:

- 𝟐𝟖.𝟓 𝐌𝐁 jina-embeddings-v2-small-en (https://huggingface.co/do-me/jina-embeddings-v2-small-en)

- 𝟏𝟎𝟗 𝐌𝐁 jina-embeddings-v2-base-en (https://huggingface.co/do-me/jina-embeddings-v2-base-en)

However, I noted, that the base model is performing quite poorly on small text chunks (a few words) while the small version seems to be unaffected. Might this be some kind of side effect due to the way they deal with large contexts?

If you want to test, you can head over to SemanticFinder (https://do-me.github.io/SemanticFinder/), go to advanced settings, choose the Jina AI base model (at the very bottom) and run with "Find". You'll see that all other models perform just fine and find "food"-related chunks but the base version doesn't.

[Havoc]

Why quantize something that is already very small (270mb)?

[pietz]

Just making up stuff here, but smaller models are great for serverless compute like functions, which would also benefit from lighter computation. Don't forget, some people are dealing with hundreds of millions of documents. Accelerating this by 4x may be worth a small performance hit.