policy-gradient / GRPO-ZeroLinks
Implementing DeepSeek R1's GRPO algorithm from scratch
☆1,372Updated last month
Alternatives and similar repositories for GRPO-Zero
Users that are interested in GRPO-Zero are comparing it to the libraries listed below
Sorting:
- Minimalistic 4D-parallelism distributed training framework for education purpose☆1,505Updated 2 months ago
- nanoGPT style version of Llama 3.1☆1,373Updated 9 months ago
- Understanding R1-Zero-Like Training: A Critical Perspective☆945Updated last week
- Single File, Single GPU, From Scratch, Efficient, Full Parameter Tuning library for "RL for LLMs"☆460Updated this week
- NanoGPT (124M) in 3 minutes☆2,600Updated this week
- The simplest, fastest repository for training/finetuning small-sized VLMs.☆3,003Updated this week
- Recipes to scale inference-time compute of open models☆1,073Updated last week
- Muon optimizer: +>30% sample efficiency with <3% wallclock overhead☆661Updated this week
- Official repository for our work on micro-budget training of large-scale diffusion models.☆1,416Updated 4 months ago
- Muon is Scalable for LLM Training☆1,049Updated 2 months ago
- Code for BLT research paper☆1,664Updated last week
- Training Large Language Model to Reason in a Continuous Latent Space☆1,120Updated 4 months ago
- UNet diffusion model in pure CUDA☆605Updated 11 months ago
- The Multilayer Perceptron Language Model☆549Updated 9 months ago
- A bibliography and survey of the papers surrounding o1☆1,193Updated 6 months ago
- LIMO: Less is More for Reasoning☆944Updated last month
- The Autograd Engine☆607Updated 8 months ago
- Minimalistic large language model 3D-parallelism training☆1,888Updated last week
- Simple RL training for reasoning☆3,584Updated last month
- Textbook on reinforcement learning from human feedback☆938Updated this week
- Build your own visual reasoning model☆368Updated last week
- An Open-source RL System from ByteDance Seed and Tsinghua AIR☆1,261Updated 3 weeks ago
- Deep learning for dummies. All the practical details and useful utilities that go into working with real models.☆793Updated last month
- System 2 Reasoning Link Collection☆834Updated 2 months ago
- Pretraining code for a large-scale depth-recurrent language model☆768Updated last week
- procedural reasoning datasets☆603Updated last week
- Large Concept Models: Language modeling in a sentence representation space☆2,206Updated 4 months ago
- Democratizing Reinforcement Learning for LLMs☆3,291Updated 2 weeks ago
- A Self-adaptation Framework🐙 that adapts LLMs for unseen tasks in real-time!☆1,065Updated 4 months ago
- [ICLR 2025] Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling☆874Updated last month