JerryWu-code / TinyZeroLinks
Deepseek R1 zero tiny version own reproduce on two A100s.
☆71Updated 8 months ago
Alternatives and similar repositories for TinyZero
Users that are interested in TinyZero are comparing it to the libraries listed below
Sorting:
- Official code for the paper, "Stop Summation: Min-Form Credit Assignment Is All Process Reward Model Needs for Reasoning"☆136Updated 2 months ago
- ☆318Updated 4 months ago
- L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning☆256Updated 4 months ago
- This is the repository that contains the source code for the Self-Evaluation Guided MCTS for online DPO.☆325Updated last year
- ☆211Updated 7 months ago
- ☆297Updated 4 months ago
- The Entropy Mechanism of Reinforcement Learning for Large Language Model Reasoning.☆340Updated 2 months ago
- OpenRFT: Adapting Reasoning Foundation Model for Domain-specific Tasks with Reinforcement Fine-Tuning☆149Updated 9 months ago
- A version of verl to support diverse tool use☆570Updated this week
- ☆207Updated 6 months ago
- Official Repository of "Learning to Reason under Off-Policy Guidance"☆330Updated this week
- A lightweight reproduction of DeepSeek-R1-Zero with indepth analysis of self-reflection behavior.☆244Updated 5 months ago
- ☆333Updated 2 months ago
- Implementation for "Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs"☆383Updated 8 months ago
- Repo of paper "Free Process Rewards without Process Labels"☆164Updated 6 months ago
- A series of technical report on Slow Thinking with LLM☆739Updated last month
- xVerify: Efficient Answer Verifier for Reasoning Model Evaluations☆131Updated 5 months ago
- Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning☆190Updated 6 months ago
- A Framework for LLM-based Multi-Agent Reinforced Training and Inference☆276Updated this week
- ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search (NeurIPS 2024)☆670Updated 8 months ago
- Pre-trained, Scalable, High-performance Reward Models via Policy Discriminative Learning.☆157Updated last week
- A simple toolkit for benchmarking LLMs on mathematical reasoning tasks. 🧮✨☆258Updated last year
- Code for Paper (ReMax: A Simple, Efficient and Effective Reinforcement Learning Method for Aligning Large Language Models)☆193Updated last year
- ☆129Updated last year
- ☆352Updated 3 months ago
- A comprehensive collection of process reward models.☆110Updated this week
- Implementation for the research paper "Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision".☆56Updated 10 months ago
- ☆341Updated 4 months ago
- The related works and background techniques about Openai o1☆222Updated 8 months ago
- Trinity-RFT is a general-purpose, flexible and scalable framework designed for reinforcement fine-tuning (RFT) of large language models (…☆356Updated last week