starcoder icon indicating copy to clipboard operation
starcoder copied to clipboard

onnx formated model

Open PrestigeDevop opened this issue 2 years ago • 5 comments
trafficstars

is it possible to release the model as serialized onnx file probably it's a good idea to release some sample code with onnx Inference engine with public restful API

PrestigeDevop avatar May 14 '23 08:05 PrestigeDevop

+1! I myself is trying to convert it, but have not done yet. Official support would be best!

Symbolk avatar May 15 '23 01:05 Symbolk

It's being added here https://github.com/huggingface/optimum/pull/1042

loubnabnl avatar Jun 13 '23 08:06 loubnabnl

It's being added here huggingface/optimum#1042

Cute!

Symbolk avatar Jun 13 '23 13:06 Symbolk

Any updates on this PR?

Thanks

wangjiyang avatar Jul 07 '23 11:07 wangjiyang

The ONNX export as well as ONNX Runtime inference is now supported through this PR in Optimum: https://github.com/huggingface/optimum/pull/1042

JingyaHuang avatar Aug 01 '23 12:08 JingyaHuang