Instructions to use onnx-community/Qwen2.5-Math-1.5B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers.js
How to use onnx-community/Qwen2.5-Math-1.5B-Instruct with Transformers.js:
// npm i @huggingface/transformers import { pipeline } from '@huggingface/transformers'; // Allocate pipeline const pipe = await pipeline('text-generation', 'onnx-community/Qwen2.5-Math-1.5B-Instruct');
Add response template
Withdrawn after checkpoint-specific response-protocol audit.
The exact checkpoint’s published examples do not establish the thinking/tool-call output protocol proposed here. Inherited family template code is insufficient evidence. Withdrawing this addition pending checkpoint-specific output validation; this is not a claim that the model cannot be prompted to use tools or reason in plain text.
Source: https://huggingface.co/Qwen/Qwen2.5-Math-1.5B-Instruct
response_template describes output parsing syntax, not a guarantee of tool-use quality. Existing chat_template formatting is unaffected.
The exact checkpoint’s published examples do not establish the thinking/tool-call output protocol proposed here. Inherited family template code is insufficient evidence. Withdrawing this addition pending checkpoint-specific output validation; this is not a claim that the model cannot be prompted to use tools or reason in plain text.