Official code implementation of Perception R1: Pioneering Perception Policy with Reinforcement Learning

Wan: Open and Advanced Large-Scale Video Generative Models

DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling

Expert Parallelism Load Balancer

DeepEP: an efficient expert-parallel communication library

A collection of LLM papers, blogs, and projects, with a focus on OpenAI o1 🍓 and reasoning techniques.

Fully open data curation for reasoning models

"Your Fully-Automated Personal AI Assistant, and Open-Source & Cost-Efficient Alternative to OpenAI's Deep Research"

A library for advanced large language model reasoning

Scalable RL solution for advanced reasoning of language models

Democratizing Reinforcement Learning for LLMs

Janus-Series: Unified Multimodal Understanding and Generation Models

Qwen2.5 is the large language model series developed by Qwen team, Alibaba Cloud.

Qwen2-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

Qwen2.5-Coder is the code version of Qwen2.5, the large language model series developed by Qwen team, Alibaba Cloud.

Agent framework and applications built upon Qwen2.x, featuring Function Calling, Code Interpreter, RAG, and Chrome extension.

The official repo of Qwen2-Audio chat & pretrained large audio language model proposed by Alibaba Cloud.

Open-Sora: Democratizing Efficient Video Production for All

Mixture-of-Experts for Large Vision-Language Models

《大语言模型》作者：赵鑫，李军毅，周昆，唐天一，文继荣

Code samples from the "Python Cookbook, 3rd Edition", published by O'Reilly & Associates, May, 2013.

A Gradio web UI for Large Language Models. Supports transformers, GPTQ, llama.cpp (ggml/gguf), Llama models.

✨✨Latest Papers and Datasets on Multimodal Large Language Models, and Their Evaluation.