Alternatives and similar repositories for open-r1

Users that are interested in open-r1 are comparing it to the libraries listed below

• Jiayi-Pan / TinyZero
  Minimal reproduction of DeepSeek R1-Zero
  ☆12,591Updated 8 months ago
• simplescaling / s1
  s1: Simple test-time scaling
  ☆6,625Updated 6 months ago
• hkust-nlp / simpleRL-reason
  Simple RL training for reasoning
  ☆3,826Updated 3 weeks ago
• deepseek-ai / DeepSeek-V3
  ☆101,121Updated 4 months ago
• vllm-project / vllm
  A high-throughput and memory-efficient inference and serving engine for LLMs
  ☆67,633Updated this week
• deepseek-ai / DeepSeek-R1
  ☆91,688Updated 6 months ago
• deepseek-ai / Janus
  Janus-Series: Unified Multimodal Understanding and Generation Models
  ☆17,665Updated 11 months ago
• unslothai / unsloth
  Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek, Qwen, Llama, Gemma, TTS 2x faster with 70% less VRAM.
  ☆50,714Updated this week
• deepseek-ai / DeepSeek-VL2
  DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding
  ☆5,182Updated 10 months ago
• volcengine / verl
  verl: Volcano Engine Reinforcement Learning for LLMs
  ☆18,310Updated this week
• rllm-org / rllm
  Democratizing Reinforcement Learning for LLMs
  ☆4,965Updated last week
• sgl-project / sglang
  SGLang is a high-performance serving framework for large language models and multimodal models.
  ☆22,343Updated this week
• QwenLM / Qwen3
  Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.
  ☆26,129Updated last week
• deepseek-ai / open-infra-index
  Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation
  ☆7,950Updated 8 months ago
• QwenLM / Qwen3-VL
  Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.
  ☆17,808Updated last week
• deepseek-ai / FlashMLA
  FlashMLA: Efficient Multi-head Latent Attention Kernels
  ☆11,964Updated last month
• huggingface / trl
  Train transformer language models with reinforcement learning.
  ☆17,005Updated this week
• OpenRLHF / OpenRLHF
  An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & TIS & vLLM & Ray & Async RL)
  ☆8,793Updated last week
• MoonshotAI / Kimi-k1.5
  ☆3,466Updated 10 months ago
• deepseek-ai / DeepEP
  DeepEP: an efficient expert-parallel communication library
  ☆8,875Updated 2 weeks ago
• NovaSky-AI / SkyThought
  Sky-T1: Train your own O1 preview model within $450
  ☆3,367Updated 6 months ago
• kvcache-ai / ktransformers
  A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations
  ☆16,344Updated this week
• meta-llama / llama-cookbook
  Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We als…
  ☆18,141Updated 2 months ago
• meta-llama / llama
  Inference code for Llama models
  ☆59,055Updated 11 months ago
• StarsfieldAI / R1-V
  Witness the aha moment of VLM with less than $3.
  ☆4,016Updated 7 months ago
• deepseek-ai / DeepSeek-Coder
  DeepSeek Coder: Let the Code Write Itself
  ☆22,645Updated 2 months ago
• deepseek-ai / DeepGEMM
  DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling
  ☆6,052Updated last week
• Dao-AILab / flash-attention
  Fast and memory-efficient exact attention
  ☆21,635Updated this week
• om-ai-lab / VLM-R1
  Solve Visual Understanding with Reinforced VLMs
  ☆5,797Updated 2 months ago
• lm-sys / FastChat
  An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
  ☆39,357Updated 7 months ago