open-thought / tiny-grpoLinks
Minimal hackable GRPO implementation
☆274Updated 6 months ago
Alternatives and similar repositories for tiny-grpo
Users that are interested in tiny-grpo are comparing it to the libraries listed below
Sorting:
- nanoGRPO is a lightweight implementation of Group Relative Policy Optimization (GRPO)☆113Updated 2 months ago
- Official repo for paper: "Reinforcement Learning for Reasoning in Small LLMs: What Works and What Doesn't"☆248Updated 2 months ago
- Tina: Tiny Reasoning Models via LoRA☆274Updated 2 months ago
- Single File, Single GPU, From Scratch, Efficient, Full Parameter Tuning library for "RL for LLMs"☆512Updated 3 weeks ago
- 🌾 OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.☆425Updated last week
- Code for the paper: "Learning to Reason without External Rewards"☆344Updated 3 weeks ago
- A project to improve skills of large language models☆501Updated this week
- Memory layers use a trainable key-value lookup mechanism to add extra parameters to a model without increasing FLOPs. Conceptually, spars…☆344Updated 7 months ago
- Large Reasoning Models☆804Updated 8 months ago
- SkyRL: A Modular Full-stack RL Library for LLMs☆679Updated last week
- ☆608Updated 3 weeks ago
- Exploring Applications of GRPO☆245Updated 3 weeks ago
- minimal GRPO implementation from scratch☆94Updated 4 months ago
- (ICML 2024) Alphazero-like Tree-Search can guide large language model decoding and training☆278Updated last year
- TTRL: Test-Time Reinforcement Learning☆745Updated 3 weeks ago
- A simplified implementation for experimenting with RLVR on GSM8K, This repository provides a starting point for exploring reasoning.☆119Updated 6 months ago
- ☆870Updated last month
- Official codebase for "Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling".☆268Updated 5 months ago
- Public repository for "The Surprising Effectiveness of Test-Time Training for Abstract Reasoning"☆321Updated 8 months ago
- An extension of the nanoGPT repository for training small MOE models.☆164Updated 4 months ago
- Understanding R1-Zero-Like Training: A Critical Perspective☆1,055Updated last week
- RLHF implementation details of OAI's 2019 codebase☆187Updated last year
- ☆206Updated 5 months ago
- ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search (NeurIPS 2024)☆656Updated 6 months ago
- ☆147Updated 8 months ago
- Parallel Scaling Law for Language Model — Beyond Parameter and Inference Time Scaling☆428Updated 2 months ago
- Scalable toolkit for efficient model reinforcement☆578Updated this week
- ☆309Updated 2 months ago
- Notes and commented code for RLHF (PPO)☆101Updated last year
- Deepseek R1 zero tiny version own reproduce on two A100s.☆70Updated 6 months ago