dirk1983
Follow
Stars
🚀 「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!
High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.
📦A portable package for running Hunyuan3D-2 on Windows. | 混元 3D 2.0 整合包
🔥 🔥 🔥 自建Docker镜像加速服务，基于官方Docker Registry 一键部署Docker、K8s、Quay、Ghcr、Mcr、Nvcr等镜像加速\管理服务。支持免服务器部署到Render\Koyeb
High-performance inference framework for large language models, focusing on efficiency, flexibility, and availability.
A simple screen parsing tool towards pure vision based GUI agent
Toolkit for linearizing PDFs for LLM datasets/training
Custom Rustdesk Api Server, include web admin ,web client, web client v2 preview and oidc login
Finetune Llama 4, DeepSeek-R1, Gemma 3 & Reasoning LLMs 2x faster with 70% less memory! 🦥
Wan: Open and Advanced Large-Scale Video Generative Models
A Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations
A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity Detection, Text Post-processing etc.
Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"
real time face swap and one-click video deepfake with only a single image
Langchain-Chatchat（原Langchain-ChatGLM）基于 Langchain 与 ChatGLM, Qwen 与 Llama 等语言模型的 RAG 与 Agent 应用 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM, Qwen and…
LivePortrait: Efficient Portrait Animation with Stitching and Retargeting Control
🤯 Lobe Chat - an open-source, modern-design AI chat framework. Supports Multi AI Providers( OpenAI / Claude 3 / Gemini / Ollama / DeepSeek / Qwen), Knowledge Base (file upload / knowledge managemen…
一个简单的本地网页界面，使用ChatTTS将文字合成为语音，同时支持对外提供API接口。A simple native web interface that uses ChatTTS to synthesize text into speech, along with support for external API interfaces.
A generative speech model for daily dialogue.
ChatLaw：A Powerful LLM Tailored for Chinese Legal. 中文法律大模型
Turn any glasses into AI-powered smart glasses