Qwen2.5-Omni is an end-to-end multimodal model by Qwen team at Alibaba Cloud, capable of understanding text, audio, vision, video, and performing real-time speech generation.

Apache ECharts is a powerful, interactive charting and data visualization library for browser

Finetune Llama 3.3, DeepSeek-R1, Gemma 3 & Reasoning LLMs 2x faster with 70% less memory! 🦥

NumPy aware dynamic Python compiler using LLVM

Baidu's open-source Sentiment Analysis System.

腾讯的离线敏感词库

Wan: Open and Advanced Large-Scale Video Generative Models

No fortress, purely open ground. OpenManus is Coming.

Open Source Deep Research Alternative to Reason and Search on Private Data. Written in Python.

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

Keep searching, reading webpages, reasoning until it finds the answer (or exceeding the token budget)

Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation

A list of AI autonomous agents

flash attention tutorial written in python, triton, cuda, cutlass

CUDA Templates for Linear Algebra Subroutines

FlashMLA: Efficient MLA decoding kernels

MoBA: Mixture of Block Attention for Long-Context LLMs

one for all free music in china (origin edition)

This repository contains the Hugging Face Agents Course.

🚀 Resume Builder 在线简历生成工具

Fast lexical search implementing BM25 in Python using Numpy, Numba and Scipy

Efficient Triton Kernels for LLM Training

Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verified research papers.

A course on aligning smol models.

Run AI Agent in your browser.

Fully open reproduction of DeepSeek-R1

Clean, minimal, accessible reproduction of DeepSeek R1-Zero