huggingface / open-r1Links
Fully open reproduction of DeepSeek-R1
☆25,581Updated last month
Alternatives and similar repositories for open-r1
Users that are interested in open-r1 are comparing it to the libraries listed below
Sorting:
- Minimal reproduction of DeepSeek R1-Zero☆12,317Updated 6 months ago
- SGLang is a fast serving framework for large language models and vision language models.☆19,094Updated last week
- s1: Simple test-time scaling☆6,585Updated 4 months ago
- verl: Volcano Engine Reinforcement Learning for LLMs☆14,648Updated this week
- Janus-Series: Unified Multimodal Understanding and Generation Models☆17,588Updated 8 months ago
- A high-throughput and memory-efficient inference and serving engine for LLMs☆60,980Updated this week
- Simple RL training for reasoning☆3,776Updated 2 months ago
- ☆99,948Updated 2 months ago
- ☆91,402Updated 4 months ago
- Democratizing Reinforcement Learning for LLMs☆4,600Updated this week
- Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.☆15,465Updated last week
- FlashMLA: Efficient Multi-head Latent Attention Kernels☆11,835Updated 3 weeks ago
- An Easy-to-use, Scalable and High-performance RLHF Framework based on Ray (PPO & GRPO & REINFORCE++ & vLLM & Ray & Dynamic Sampling & Asy…☆8,228Updated this week
- Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation☆7,928Updated 5 months ago
- DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding☆5,094Updated 8 months ago
- Sky-T1: Train your own O1 preview model within $450☆3,341Updated 3 months ago
- Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.☆47,355Updated this week
- Train transformer language models with reinforcement learning.☆16,012Updated this week
- Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)☆60,848Updated this week
- Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.☆12,038Updated last month
- DeepEP: an efficient expert-parallel communication library☆8,662Updated this week
- ☆3,467Updated 7 months ago
- Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.☆25,085Updated 2 weeks ago
- Witness the aha moment of VLM with less than $3.☆3,964Updated 5 months ago
- Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 500+ LLMs (Qwen3, Qwen3-MoE, Llama4, GLM4.5, InternLM3, DeepSeek-R1, ...) and 200+ MLLMs (…☆10,723Updated this week
- Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We als…☆17,979Updated this week
- DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model☆4,950Updated last year
- A Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations☆15,207Updated last week
- Solve Visual Understanding with Reinforced VLMs☆5,652Updated last week
- LMDeploy is a toolkit for compressing, deploying, and serving LLMs.☆7,199Updated this week