modelscope / Trinity-RFTLinks
Trinity-RFT is a general-purpose, flexible and scalable framework designed for reinforcement fine-tuning (RFT) of large language models (LLM).
☆110Updated this week
Alternatives and similar repositories for Trinity-RFT
Users that are interested in Trinity-RFT are comparing it to the libraries listed below
Sorting:
- A Comprehensive Survey on Long Context Language Modeling☆147Updated this week
- ☆63Updated 6 months ago
- ☆202Updated 3 months ago
- xVerify: Efficient Answer Verifier for Reasoning Model Evaluations☆106Updated last month
- [ICLR 2025] 🧬 RegMix: Data Mixture as Regression for Language Model Pre-training (Spotlight)☆141Updated 3 months ago
- ☆100Updated 8 months ago
- [ACL 2024] Long-Context Language Modeling with Parallel Encodings☆153Updated 11 months ago
- Implementation for the research paper "Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision".☆54Updated 6 months ago
- A research repo for experiments about Reinforcement Finetuning☆47Updated 2 months ago
- ☆210Updated 2 weeks ago
- Model merging is a highly efficient approach for long-to-short reasoning.☆56Updated this week