policy-gradient / GRPO-ZeroLinks
Implementing DeepSeek R1's GRPO algorithm from scratch
☆1,496Updated 3 months ago
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☆1,619Updated 3 weeks ago
- nanoGPT style version of Llama 3.1☆1,409Updated 11 months ago
- NanoGPT (124M) in 3 minutes☆2,892Updated 2 weeks ago
- Code for BLT research paper☆1,744Updated 2 months ago
- The simplest, fastest repository for training/finetuning small-sized VLMs.☆3,799Updated last week
- Textbook on reinforcement learning from human feedback☆1,137Updated last week
- Single File, Single GPU, From Scratch, Efficient, Full Parameter Tuning library for "RL for LLMs"☆506Updated 3 weeks ago
- Muon is an optimizer for hidden layers in neural networks☆1,314Updated 2 weeks ago
- Training Large Language Model to Reason in a Continuous Latent Space☆1,216Updated 6 months ago
- Understanding R1-Zero-Like Training: A Critical Perspective☆1,048Updated last week
- Muon is Scalable for LLM Training☆1,223Updated 4 months ago
- Official repository for our work on micro-budget training of large-scale diffusion models.☆1,501Updated 6 months ago
- Recipes to scale inference-time compute of open models☆1,110Updated 2 months ago
- Minimalistic large language model 3D-parallelism training☆2,068Updated 3 weeks ago
- procedural reasoning datasets☆998Updated this week
- A PyTorch native platform for training generative AI models☆4,125Updated this week
- A bibliography and survey of the papers surrounding o1☆1,207Updated 8 months ago
- Simple RL training for reasoning☆3,693Updated 3 months ago
- The Autograd Engine☆623Updated 10 months ago
- An Open-source RL System from ByteDance Seed and Tsinghua AIR☆1,470Updated 2 months ago
- The Multilayer Perceptron Language Model☆556Updated 11 months ago
- Verifiers for LLM Reinforcement Learning☆1,621Updated this week
- UNet diffusion model in pure CUDA☆612Updated last year
- Pretraining and inference code for a large-scale depth-recurrent language model☆806Updated 2 weeks ago
- Unofficial implementation of Titans, SOTA memory for transformers, in Pytorch☆1,421Updated last month
- [COLM 2025] LIMO: Less is More for Reasoning☆986Updated 3 weeks ago
- 🚀 Efficient implementations of state-of-the-art linear attention models☆2,950Updated this week
- Puzzles for learning Triton☆1,786Updated 8 months ago
- RAGEN leverages reinforcement learning to train LLM reasoning agents in interactive, stochastic environments.☆2,167Updated last week
- Democratizing Reinforcement Learning for LLMs☆3,910Updated last week