policy-gradient / GRPO-ZeroLinks
Implementing DeepSeek R1's GRPO algorithm from scratch
☆1,587Updated 5 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☆1,836Updated last month
- nanoGPT style version of Llama 3.1☆1,427Updated last year
- NanoGPT (124M) in 3 minutes☆3,145Updated 2 months ago
- Textbook on reinforcement learning from human feedback☆1,242Updated 2 weeks ago
- The simplest, fastest repository for training/finetuning small-sized VLMs.☆4,063Updated 3 weeks ago
- Training Large Language Model to Reason in a Continuous Latent Space☆1,272Updated last month
- Understanding R1-Zero-Like Training: A Critical Perspective☆1,100Updated last month
- Code for BLT research paper☆1,985Updated 4 months ago
- Muon is an optimizer for hidden layers in neural networks☆1,767Updated 2 months ago
- Single File, Single GPU, From Scratch, Efficient, Full Parameter Tuning library for "RL for LLMs"☆535Updated 2 months ago
- Official repository for our work on micro-budget training of large-scale diffusion models.☆1,511Updated 8 months ago
- Environments for LLM Reinforcement Learning☆3,222Updated this week
- [NeurIPS 2025 Spotlight] Reasoning Environments for Reinforcement Learning with Verifiable Rewards☆1,161Updated this week
- Recipes to scale inference-time compute of open models☆1,109Updated 4 months ago
- Minimalistic large language model 3D-parallelism training☆2,239Updated last month
- Simple RL training for reasoning☆3,754Updated 2 months ago
- Muon is Scalable for LLM Training☆1,318Updated 2 months ago
- 🚀 Efficient implementations of state-of-the-art linear attention models☆3,404Updated last week
- Democratizing Reinforcement Learning for LLMs☆4,357Updated this week
- Scalable toolkit for efficient model reinforcement☆910Updated this week
- A bibliography and survey of the papers surrounding o1☆1,208Updated 10 months ago
- The Multilayer Perceptron Language Model☆566Updated last year
- slime is an LLM post-training framework for RL Scaling.☆1,915Updated last week
- [COLM 2025] LIMO: Less is More for Reasoning☆1,022Updated 2 months ago
- Large Concept Models: Language modeling in a sentence representation space☆2,285Updated 8 months ago
- UNet diffusion model in pure CUDA☆647Updated last year
- [ICLR 2025] Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling☆912Updated 5 months ago
- Best practices & guides on how to write distributed pytorch training code☆487Updated 7 months ago
- Puzzles for learning Triton☆2,008Updated 10 months ago
- The Autograd Engine☆634Updated last year