NetEase-FuXi / EETQ

Easy and Efficient Quantization for Transformers
Apache License 2.0
174 stars 14 forks source link

Integration with Hugging Face transformers library #13

Closed younesbelkada closed 4 months ago

younesbelkada commented 5 months ago

Hi there!

We recently created an HfQuantizer to facilitate the integration of new quantization libraries on HF transformers: https://huggingface.co/docs/transformers/main/en/hf_quantizer - the code changes should be quite easy and the whole community would benefit from an easy API !

See an example here: https://github.com/huggingface/transformers/pull/28928 of a recent integration

I can also help for the integration if needed !

Thanks in advance

SidaZh commented 5 months ago

@younesbelkada Excellent work!We are very willing to contribute eetq to the hf community.

younesbelkada commented 5 months ago

Nice, thank you @SidaZh ! Let us know if you need any help kick-offing the PR ! Looking forward to your contribution !