metadata
license: cc-by-nc-4.0
library_name: transformers
pipeline_tag: 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