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
  ☆12,085Updated 3 months ago
• deepseek-ai / DeepSeek-R1
  ☆90,738Updated last month
• simplescaling / s1
  s1: Simple test-time scaling
  ☆6,519Updated last month
• volcengine / verl
  verl: Volcano Engine Reinforcement Learning for LLMs
  ☆11,878Updated this week
• deepseek-ai / DeepSeek-V3
  ☆98,457Updated last month
• vllm-project / vllm
  A high-throughput and memory-efficient inference and serving engine for LLMs
  ☆53,703Updated this week
• QwenLM / Qwen3
  Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.
  ☆23,743Updated last week
• hkust-nlp / simpleRL-reason
  Simple RL training for reasoning
  ☆3,699Updated this week
• deepseek-ai / Janus
  Janus-Series: Unified Multimodal Understanding and Generation Models
  ☆17,489Updated 6 months ago
• sgl-project / sglang
  SGLang is a fast serving framework for large language models and vision language models.
  ☆16,576Updated this week
• deepseek-ai / DeepSeek-Coder
  DeepSeek Coder: Let the Code Write Itself
  ☆21,973Updated last year
• MoonshotAI / Kimi-k1.5
  ☆3,456Updated 4 months ago
• rllm-org / rllm
  Democratizing Reinforcement Learning for LLMs
  ☆3,962Updated this week
• StarsfieldAI / R1-V
  Witness the aha moment of VLM with less than $3.
  ☆3,882Updated 2 months ago
• huggingface / trl
  Train transformer language models with reinforcement learning.
  ☆14,863Updated this week
• unslothai / unsloth
  Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train Qwen3, Llama 4, DeepSeek-R1, Gemma 3, TTS 2x faster with 70% less VRAM.
  ☆42,983Updated last week
• QwenLM / Qwen2.5-VL
  Qwen2.5-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.
  ☆11,866Updated 2 months ago
• deepseek-ai / DeepSeek-VL2
  DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding
  ☆4,996Updated 5 months ago
• QwenLM / Qwen-Agent
  Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.
  ☆10,686Updated last week
• Dao-AILab / flash-attention
  Fast and memory-efficient exact attention
  ☆18,656Updated last week
• OpenRLHF / OpenRLHF
  An Easy-to-use, Scalable and High-performance RLHF Framework based on Ray (PPO & GRPO & REINFORCE++ & vLLM & Ray & Dynamic Sampling & Asy…
  ☆7,552Updated this week
• om-ai-lab / VLM-R1
  Solve Visual Understanding with Reinforced VLMs
  ☆5,396Updated last month
• deepseek-ai / open-infra-index
  Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation
  ☆7,880Updated 2 months ago
• huggingface / smolagents
  🤗 smolagents: a barebones library for agents that think in code.
  ☆21,754Updated this week
• hiyouga / LLaMA-Factory
  Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
  ☆55,420Updated last week
• modelscope / ms-swift
  Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 500+ LLMs (Qwen3, Qwen3-MoE, Llama4, GLM4.5, InternLM3, DeepSeek-R1, ...) and 200+ MLLMs (…
  ☆9,054Updated this week
• deepseek-ai / DeepSeek-V2
  DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
  ☆4,936Updated 10 months ago
• NovaSky-AI / SkyThought
  Sky-T1: Train your own O1 preview model within $450
  ☆3,320Updated 3 weeks ago
• BerriAI / litellm
  Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sag…
  ☆26,770Updated this week
• deepseek-ai / DeepEP
  DeepEP: an efficient expert-parallel communication library
  ☆8,340Updated this week