Instructions to use onnx-community/LFM2-2.6B-ONNX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers.js
How to use onnx-community/LFM2-2.6B-ONNX with Transformers.js:
// npm i @huggingface/transformers import { pipeline } from '@huggingface/transformers'; // Allocate pipeline const pipe = await pipeline('text-generation', 'onnx-community/LFM2-2.6B-ONNX');
Add response template parsing
#1
by nico-martin HF Staff - opened
Add checkpoint-specific response parsing for thinking, tool_calls, content.
Retain the checkpoint’s thinking, tool-call, and content parsing regions.
Source: https://huggingface.co/LiquidAI/LFM2-2.6B
This template describes the checkpoint’s output protocol; it does not imply that every response contains every region or guarantee tool-use quality.
stop spamming my notifications lmoa
Xenova changed pull request status to merged