Instructions to use onnx-community/LFM2-350M-Math-ONNX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers.js
How to use onnx-community/LFM2-350M-Math-ONNX with Transformers.js:
// npm i @huggingface/transformers import { pipeline } from '@huggingface/transformers'; // Allocate pipeline const pipe = await pipeline('text-generation', 'onnx-community/LFM2-350M-Math-ONNX');
Standardize parsed reasoning as reasoning_content
#3
by nico-martin HF Staff - opened
Response parsing now uses the canonical assistant-message key reasoning_content. Protocol delimiters and parser behavior remain unchanged.
nico-martin changed pull request status to merged