InternLM / POLARLinks
Pre-trained, Scalable, High-performance Reward Models via Policy Discriminative Learning.
☆56Updated this week
Alternatives and similar repositories for POLAR
Users that are interested in POLAR are comparing it to the libraries listed below
Sorting:
- OpenRFT: Adapting Reasoning Foundation Model for Domain-specific Tasks with Reinforcement Fine-Tuning☆145Updated 6 months ago
- Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning☆188Updated 3 months ago
- xVerify: Efficient Answer Verifier for Reasoning Model Evaluations☆119Updated 2 months ago
- CPPO: Accelerating the Training of Group Relative Policy Optimization-Based Reasoning Models☆142Updated last month
- ☆205Updated 4 months ago
- A comprehensive collection of process reward models.☆95Updated 2 weeks ago
- ☆238Updated last month
- Tool-Star: Empowering LLM-brained Multi-Tool Reasoner via Reinforcement Learning☆197Updated last week
- ☆303Updated last month
- Extrapolating RLVR to General Domains without Verifiers☆112Updated 2 weeks ago
- Rethinking RL Scaling for Vision Language Models: A Transparent, From-Scratch Framework and Comprehensive Evaluation Scheme☆133Updated 3 months ago
- Official Repository of "Learning to Reason under Off-Policy Guidance"☆249Updated last month
- The Entropy Mechanism of Reinforcement Learning for Large Language Model Reasoning.☆237Updated 2 weeks ago
- ☆266Updated last month
- ☆154Updated 2 months ago
- L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning☆226Updated 2 months ago
- Official codebase for "GenPRM: Scaling Test-Time Compute of Process Reward Models via Generative Reasoning".☆78Updated last month
- A version of verl to support tool use☆288Updated this week
- ☆147Updated 5 months ago
- A Comprehensive Survey on Long Context Language Modeling☆161Updated this week
- a-m-team's exploration in large language modeling☆173Updated last month
- A lightweight reproduction of DeepSeek-R1-Zero with indepth analysis of self-reflection behavior.☆244Updated 2 months ago
- The related works and background techniques about Openai o1☆223Updated 6 months ago
- An Easy-to-use, Scalable and High-performance RLHF Framework designed for Multimodal Models.☆135Updated 3 months ago
- ☆186Updated this week
- ☆59Updated 3 weeks ago
- MMR1: Advancing the Frontiers of Multimodal Reasoning☆162Updated 3 months ago
- Implementation for "Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs"☆372Updated 5 months ago
- [NeurIPS 2024] MATH-Vision dataset and code to measure multimodal mathematical reasoning capabilities.☆108Updated last month
- Trinity-RFT is a general-purpose, flexible and scalable framework designed for reinforcement fine-tuning (RFT) of large language models (…☆136Updated this week