JHU-CLSP / RATIONALYSTLinks
Code for RATIONALYST: Pre-training Process-Supervision for Improving Reasoning https://arxiv.org/pdf/2410.01044
☆35Updated last year
Alternatives and similar repositories for RATIONALYST
Users that are interested in RATIONALYST are comparing it to the libraries listed below
Sorting:
- Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment☆60Updated last year
- Code for EMNLP 2024 paper "Learn Beyond The Answer: Training Language Models with Reflection for Mathematical Reasoning"☆55Updated last year
- Code for the arXiv preprint "The Unreasonable Effectiveness of Easy Training Data"☆48Updated last year
- The official repository for SkyLadder: Better and Faster Pretraining via Context Window Scheduling☆34Updated last month
- Repository for NPHardEval, a quantified-dynamic benchmark of LLMs☆59Updated last year
- Aioli: A unified optimization framework for language model data mixing☆27Updated 8 months ago
- Verifiers for LLM Reinforcement Learning☆74Updated 5 months ago