deepseek-r1

19 projects share this GitHub topic

Lines connect members that are measurably related to each other. Dot size reflects stars.

🧬 Members

🔥 MaxKB is an open-source platform for building enterprise-grade agents. …

Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-V4, GLM-5.1, InternLM3, Llama4,…

Solve Visual Understanding with Reinforced VLMs

Awesome-LLM-Inference

📚A curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4,…

Skywork-R1V is an advanced multimodal AI model series developed by Skywork AI, specializing in…

Awesome-RL-for-LRMs

A Survey of Reinforcement Learning for Large Reasoning Models

verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the…

Local CLI Copilot, powered by Ollama. 💻🦙

Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey

A highly optimized LLM inference acceleration engine for Llama and its variants.

train-deepseek-r1

Building DeepSeek R1 from Scratch

deepseek java sdk

Awesome-Long-Chain-of-Thought-Reasoning

Latest Advances on Long Chain-of-Thought Reasoning

VisualThinker-R1-Zero

Explore the Multimodal “Aha Moment” on 2B Model

[NeurIPS 2025 Spotlight] LLM post-training suite — featuring ReasonFlux, ReasonFlux-PRM, and…

A Framework for LLM-based Multi-Agent Reinforced Training and Inference

Transformers-for-NLP-and-Computer-Vision-3rd-Edition

Transformers 3rd Edition

[EMNLP 2025] OmniThink: Expanding Knowledge Boundaries in Machine Writing through Thinking

Awesome-LLM-Reasoning-with-NeSy

✨✨Latest Advances on Neuro-Symbolic Learning in the era of Large Language Models

🔗 Related families

grpo 19 deepseek 88 chain-of-thought 22 deepseek-v3 4 embedding 16 multimodal 70 agent-framework 71 llama3 7

Measured from GitHub topics shared by both projects, weighted by how rare each topic is.