policy-gradient / GRPO-ZeroLinks
Implementing DeepSeek R1's GRPO algorithm from scratch
☆1,621Updated 6 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☆1,856Updated last month
- nanoGPT style version of Llama 3.1☆1,438Updated last year
- Textbook on reinforcement learning from human feedback☆1,266Updated 3 weeks ago
- NanoGPT (124M) in 3 minutes☆3,565Updated last week
- Code for BLT research paper☆1,995Updated 5 months ago
- Muon is an optimizer for hidden layers in neural networks☆1,888Updated 3 months ago
- Training Large Language Model to Reason in a Continuous Latent Space☆1,297Updated 2 months ago
- Single File, Single GPU, From Scratch, Efficient, Full Parameter Tuning library for "RL for LLMs"☆538Updated 2 weeks ago
- Understanding R1-Zero-Like Training: A Critical Perspective☆1,126Updated last month
- The simplest, fastest repository for training/finetuning small-sized VLMs.☆4,136Updated last week
- [NeurIPS 2025 Spotlight] Reasoning Environments for Reinforcement Learning with Verifiable Rewards☆1,194Updated 2 weeks ago
- Environments for LLM Reinforcement Learning☆3,338Updated this week
- Official repository for our work on micro-budget training of large-scale diffusion models.☆1,517Updated 9 months ago
- Muon is Scalable for LLM Training☆1,336Updated 2 months ago
- Recipes to scale inference-time compute of open models☆1,111Updated 5 months ago
- Minimalistic large language model 3D-parallelism training☆2,267Updated last month
- A bibliography and survey of the papers surrounding o1☆1,209Updated 11 months ago
- The Multilayer Perceptron Language Model☆571Updated last year
- Scalable toolkit for efficient model reinforcement☆931Updated last week
- Pretraining and inference code for a large-scale depth-recurrent language model☆836Updated last week
- [COLM 2025] LIMO: Less is More for Reasoning☆1,037Updated 2 months ago
- Simple RL training for reasoning☆3,773Updated 2 months ago
- Minimal and annotated implementations of key ideas from modern deep learning research.☆1,155Updated 3 weeks ago
- Deep learning for dummies. All the practical details and useful utilities that go into working with real models.☆820Updated 2 months ago
- slime is an LLM post-training framework for RL Scaling.☆2,170Updated this week
- Implementation of the sparse attention pattern proposed by the Deepseek team in their "Native Sparse Attention" paper☆772Updated 2 months ago
- A PyTorch native platform for training generative AI models☆4,561Updated this week
- 🚀 Efficient implementations of state-of-the-art linear attention models☆3,517Updated this week
- Dream 7B, a large diffusion language model☆1,018Updated 3 weeks ago
- The Autograd Engine☆636Updated last year