RoadQAQ/ReLIFT-Qwen2.5-Math-7B-Zero
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity
Files
2b7331bf30e49bef39c639440c5b0025adc65fea
ReLIFT-Qwen2.5-Math-7B-Zero/README.md
ModelHub XC 2b7331bf30 初始化项目，由ModelHub XC社区提供模型 
Model: RoadQAQ/ReLIFT-Qwen2.5-Math-7B-Zero
Source: Original Platform
2026-08-27 16:20:32 +08:00

432 B
Raw Blame History

license, library_name, pipeline_tag
license library_name pipeline_tag
cc-by-nc-4.0 transformers question-answering

This repository contains the ReLIFT model presented in Learning What Reinforcement Learning Can't: Interleaved Online Fine-Tuning for Hardest Questions.

Code: https://github.com/TheRoadQaQ/ReLIFT

Hugging Face Collection: https://huggingface.co/collections/RoadQAQ/relift-684535e199a909cad16d8b05