dvlab-research / Step-DPOLinks
Implementation for "Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs"
☆384Updated 9 months ago
Alternatives and similar repositories for Step-DPO
Users that are interested in Step-DPO are comparing it to the libraries listed below
Sorting:
- This is the repository that contains the source code for the Self-Evaluation Guided MCTS for online DPO.☆327Updated last year
- ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search (NeurIPS 2024)☆673Updated 9 months ago
- The related works and background techniques about Openai o1☆222Updated 9 months ago
- ☆342Updated 4 months ago
- Official Repository of "Learning to Reason under Off-Policy Guidance"☆348Updated 3 weeks ago
- The Entropy Mechanism of Reinforcement Learning for Large Language Model Reasoning.☆350Updated 3 months ago
- L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning☆258Updated 5 months ago
- A series of technical report on Slow Thinking with LLM☆739Updated 2 months ago
- Official code for the paper, "Stop Summation: Min-Form Credit Assignment Is All Process Reward Model Needs for Reasoning"☆138Updated 3 months ago
- ☆323Updated 4 months ago
- Codes and Data for Scaling Relationship on Learning Mathematical Reasoning with Large Language Models☆267Updated last year
- A version of verl to support diverse tool use☆607Updated last week
- ☆300Updated 5 months ago
- A comprehensive collection of process reward models.☆114Updated 3 weeks ago
- ☆211Updated 8 months ago
- ☆275Updated 3 months ago
- Awesome-Long2short-on-LRMs is a collection of state-of-the-art, novel, exciting long2short methods on large reasoning models. It contains…☆252Updated 2 months ago
- A simple toolkit for benchmarking LLMs on mathematical reasoning tasks. 🧮✨☆259Updated last year
- ☆548Updated 9 months ago
- [ICML 2024] LESS: Selecting Influential Data for Targeted Instruction Tuning☆496Updated last year
- A lightweight reproduction of DeepSeek-R1-Zero with indepth analysis of self-reflection behavior.☆247Updated 6 months ago
- ☆365Updated last week
- LoRAMoE: Revolutionizing Mixture of Experts for Maintaining World Knowledge in Language Model Alignment☆380Updated last year
- 😎 A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, Agent, and Beyond☆308Updated this week
- ☆312Updated last year
- Extrapolating RLVR to General Domains without Verifiers☆174Updated 2 months ago
- Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning☆189Updated 7 months ago
- Trinity-RFT is a general-purpose, flexible and scalable framework designed for reinforcement fine-tuning (RFT) of large language models (…☆369Updated this week
- xVerify: Efficient Answer Verifier for Reasoning Model Evaluations☆135Updated 6 months ago
- End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning☆305Updated last month