Instructions to use Xenova/codegen-350M-mono with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers.js
How to use Xenova/codegen-350M-mono with Transformers.js:
// npm i @huggingface/transformers import { pipeline } from '@huggingface/transformers'; // Allocate pipeline const pipe = await pipeline('text-generation', 'Xenova/codegen-350M-mono');
Can't get the right Onnx from conversion process
#2
by Pipper - opened
@Xenova would you please share your environment deps for converting torch models to onnx. The generation process always either leads to IR version mismatch 9!=8 or Onnxruntime-common cannot create a session. thx
Hi there! Sorry for the late reply, but here are the versions I use to convert transformers.js models: https://github.com/xenova/transformers.js/blob/main/scripts/requirements.txt
Thanks, that was a onnxruntime version mismatch. Great work!
Great! I'll close for now then :)
Xenova changed discussion status to closed
