huggingface / open-r1Links
Fully open reproduction of DeepSeek-R1
☆25,309Updated 2 weeks ago
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☆12,138Updated 4 months ago
- ☆90,949Updated 2 months ago
- s1: Simple test-time scaling☆6,537Updated 2 months ago
- ☆98,989Updated this week
- SGLang is a fast serving framework for large language models and vision language models.☆17,106Updated this week
- verl: Volcano Engine Reinforcement Learning for LLMs☆12,563Updated this week
- Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.☆24,200Updated 2 weeks ago
- Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation☆7,901Updated 3 months ago
- Qwen2.5-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.☆12,224Updated 3 months ago
- Janus-Series: Unified Multimodal Understanding and Generation Models☆17,512Updated 6 months ago
- FlashMLA: Efficient MLA kernels☆11,699Updated last week
- Simple RL training for reasoning☆3,728Updated 3 weeks ago
- ☆3,464Updated 5 months ago
- Democratizing Reinforcement Learning for LLMs☆4,043Updated this week
- Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, Qwen3, Llama 4, DeepSeek-R1, Gemma 3, TTS 2x faster with 70% less…☆44,634Updated this week
- Train transformer language models with reinforcement learning.☆15,174Updated last week
- Fast and memory-efficient exact attention☆19,099Updated this week
- A high-throughput and memory-efficient inference and serving engine for LLMs☆56,349Updated this week
- An Easy-to-use, Scalable and High-performance RLHF Framework based on Ray (PPO & GRPO & REINFORCE++ & vLLM & Ray & Dynamic Sampling & Asy…☆7,756Updated this week
- DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding☆5,026Updated 6 months ago
- A collection of LLM papers, blogs, and projects, with a focus on OpenAI o1 🍓 and reasoning techniques.☆6,820Updated last week
- DeepEP: an efficient expert-parallel communication library☆8,422Updated last week
- Sky-T1: Train your own O1 preview model within $450☆3,319Updated last month
- A Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations☆14,902Updated 3 weeks ago
- DeepSeek Coder: Let the Code Write Itself☆22,051Updated last year
- Witness the aha moment of VLM with less than $3.☆3,911Updated 3 months ago
- [NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.☆23,378Updated last year
- Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 500+ LLMs (Qwen3, Qwen3-MoE, Llama4, GLM4.5, InternLM3, DeepSeek-R1, ...) and 200+ MLLMs (…☆9,436Updated this week
- 🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.☆19,390Updated this week
- Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"☆12,575Updated 8 months ago