policy-gradient / GRPO-ZeroLinks
Implementing DeepSeek R1's GRPO algorithm from scratch
☆1,417Updated 2 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☆1,548Updated 2 weeks ago
- NanoGPT (124M) in 3 minutes☆2,660Updated this week
- nanoGPT style version of Llama 3.1☆1,380Updated 10 months ago
- Recipes to scale inference-time compute of open models☆1,095Updated 3 weeks ago
- The simplest, fastest repository for training/finetuning small-sized VLMs.☆3,247Updated last week
- Single File, Single GPU, From Scratch, Efficient, Full Parameter Tuning library for "RL for LLMs"☆474Updated 3 weeks ago
- Muon: An optimizer for hidden layers in neural networks☆766Updated last week
- Textbook on reinforcement learning from human feedback☆1,038Updated this week
- UNet diffusion model in pure CUDA☆608Updated 11 months ago
- A PyTorch native platform for training generative AI models☆3,933Updated this week
- Understanding R1-Zero-Like Training: A Critical Perspective☆988Updated 3 weeks ago
- Official repository for our work on micro-budget training of large-scale diffusion models.☆1,479Updated 5 months ago
- Training Large Language Model to Reason in a Continuous Latent Space☆1,155Updated 4 months ago
- 🚀 Efficient implementations of state-of-the-art linear attention models in Torch and Triton☆2,697Updated this week
- Best practices & guides on how to write distributed pytorch training code☆441Updated 3 months ago
- Minimalistic large language model 3D-parallelism training☆1,926Updated last week
- Muon is Scalable for LLM Training☆1,077Updated 2 months ago
- Code for BLT research paper☆1,683Updated 3 weeks ago
- procedural reasoning datasets☆841Updated last week
- LIMO: Less is More for Reasoning☆960Updated 2 months ago
- Puzzles for learning Triton☆1,695Updated 7 months ago
- A bibliography and survey of the papers surrounding o1☆1,199Updated 7 months ago
- Pretraining code for a large-scale depth-recurrent language model☆782Updated last week
- The Autograd Engine☆616Updated 9 months ago
- Build your own visual reasoning model☆381Updated this week
- Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.☆4,596Updated this week
- Verifiers for LLM Reinforcement Learning☆1,290Updated last week
- Large Concept Models: Language modeling in a sentence representation space☆2,227Updated 4 months ago
- Tile primitives for speedy kernels☆2,457Updated last week
- Simple RL training for reasoning☆3,627Updated 2 months ago