Snowflake

/

snowflake-arctic-embed-s

like 25

Follow

Snowflake 745

The ONNX files were contributed without a conversion script by HuggingFace staff member @Xenova here, so you may want to ping @Xenova directly.

I believe he uses quantize.py, I think in particular these lines are in charge of the q4 quantization: https://github.com/xenova/transformers.js/blob/v3/scripts/quantize.py#L188-L208

P.s. are you getting good results with that quantization?

Yes Quantization is increasing good speed especially on CPU

comparison between float32 and float16 -> 99% similarity
comparison between float32 and int8 -> 97% similarity

I calculated Similarity on over 80+ 2000 characters long text pieces by cosine similarity