Model: RoadQAQ/ReLIFT-Qwen2.5-Math-7B-Zero Source: Original Platform
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
Description