JerryWu-code / TinyZeroLinks
Deepseek R1 zero tiny version own reproduce on two A100s.
☆70Updated 6 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"☆132Updated 3 weeks ago
- ☆309Updated 2 months ago
- This is the repository that contains the source code for the Self-Evaluation Guided MCTS for online DPO.☆319Updated last year
- L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning☆234Updated 2 months ago
- A series of technical report on Slow Thinking with LLM☆715Updated 2 months ago
- ☆263Updated 2 months ago
- Official Repository of "Learning to Reason under Off-Policy Guidance"☆268Updated 3 weeks ago
- A version of verl to support tool use☆315Updated this week
- ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search (NeurIPS 2024)☆656Updated 6 months ago
- OpenRFT: Adapting Reasoning Foundation Model for Domain-specific Tasks with Reinforcement Fine-Tuning☆147Updated 7 months ago
- Implementation for "Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs"☆376Updated 6 months ago
- A lightweight reproduction of DeepSeek-R1-Zero with indepth analysis of self-reflection behavior.☆245Updated 3 months ago
- ☆337Updated 2 months ago
- The Entropy Mechanism of Reinforcement Learning for Large Language Model Reasoning.☆282Updated 3 weeks ago
- ☆205Updated 5 months ago
- ☆545Updated 7 months ago
- A simple toolkit for benchmarking LLMs on mathematical reasoning tasks. 🧮✨☆239Updated last year
- xVerify: Efficient Answer Verifier for Reasoning Model Evaluations☆127Updated 3 months ago
- The related works and background techniques about Openai o1☆224Updated 7 months ago
- A Framework for LLM-based Multi-Agent Reinforced Training and Inference☆185Updated this week
- ☆323Updated last week
- ☆203Updated 4 months ago
- Reference implementation for Token-level Direct Preference Optimization(TDPO)☆146Updated 5 months ago
- ☆300Updated last month
- ☆129Updated last year
- Research Code for preprint "Optimizing Test-Time Compute via Meta Reinforcement Finetuning".☆100Updated 3 weeks ago
- Repo of paper "Free Process Rewards without Process Labels"☆161Updated 4 months ago
- Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning☆188Updated 4 months ago
- Code for Paper (ReMax: A Simple, Efficient and Effective Reinforcement Learning Method for Aligning Large Language Models)☆189Updated last year
- ReasonFlux Series - A family of LLM post-training algorithms focusing on data selection, reinforcement learning, and inference scaling☆470Updated 2 weeks ago