Stars
利用AI大模型，一键生成高清短视频 Generate short videos with one click using AI LLM.
Codebase for Berkeley Humanoid Lite
MAGI-1: Autoregressive Video Generation at Scale
Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting yo…
Finetune Qwen3, Llama 4, TTS, DeepSeek-R1 & Gemma 3 LLMs 2x faster with 70% less memory! 🦥
🚀 「大模型」1小时从0训练26M参数的视觉多模态VLM！🌏 Train a 26M-parameter VLM from scratch in just 1 hours!
🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT！🌏 Train a 26M-parameter GPT from scratch in just 2h!
The Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems
User-friendly Desktop Client App for AI Models/LLMs (GPT, Claude, Gemini, Ollama...)
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
MiniCPM3-4B: An edge-side LLM that surpasses GPT-3.5-Turbo.
The simplest, fastest repository for training/finetuning medium-sized GPTs.
real time face swap and one-click video deepfake with only a single image
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
Generic automation framework for acceptance testing and RPA
Instant voice cloning by MIT and MyShell. Audio foundation model.
a state-of-the-art-level open visual language model | 多模态预训练模型
Open-Sora: Democratizing Efficient Video Production for All
Deezer source separation library including pretrained models.
免费IM系统，IM即时通信消息系统(含一对一文字聊天，群聊，聊天室)，免费一对一voip实时通话，录屏，webrtc服务端，免费直播连麦，互动直播，视频直播，RTSP拉流，RTMP推流，语音对讲，免费在线会议，视频会议等服务端程序，支持物联网平台，✨万水千山总是情，来个star行不行✨
lightweight, standalone C++ inference engine for Google's Gemma models.
Get up and running with Llama 3.3, DeepSeek-R1, Phi-4, Gemma 3, Mistral Small 3.1 and other large language models.
🕵️♂️ All-in-one OSINT tool for analysing any website