James Chang's repositories
Agent-Attention
Official repository of Agent Attention
anything-llm
Open-source ChatGPT experience for both open and closed source LLMs, embedders, and vector databases. Unlimited documents, messages, and concurrent users with permission management in one app. 👉 Desktop app beta: https://mintplexlabs.typeform.com/to/sFgD2TIb
APE
Aligning and Prompting Everything All at Once for Universal Visual Perception
ChatLaw
中文法律大模型
chroma
the AI-native open-source embedding database
ColossalAI
Making large AI models cheaper, faster and more accessible
data-gradients
Computer Vision dataset analysis
dreamtalk
Official implementations for paper: DreamTalk: When Expressive Talking Head Generation Meets Diffusion Probabilistic Models
gpu-docker-api
Easier than K8s to lift and lower the gpu number of docker container and scale capacity size of volume.
GTA
Official repository for NeurIPS 2023 paper "Global-correlated 3D-decoupling Transformer for Clothed Avatar Reconstruction"
H2O_NIPS23
[NeurIPS'23] H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.
HubFrontend
集成 GPT 问答、Midjourney 绘画等一站式服务的系统
i2vgen-xl
Official repo for VGen: a holistic video generation ecosystem for video generation building on diffusion models
lightning-attention
Lightning Attention-2: A Free Lunch for Handling Unlimited Sequence Lengths in Large Language Models
Linly-Talker
Digital Avatar Conversational System - Linly-Talker. 😄✨ Linly-Talker is an intelligent AI system that combines large language models (LLMs) with visual models to create a novel human-AI interaction method. 🤝🤖 It integrates various technologies like Whisper, Linly, Microsoft Speech Services, and SadTalker talking head generation system. 🌟🔬
LLaMA-Pro
Progressive LLaMA with Block Expansion.
lobe-chat
🤖 Lobe Chat - an open-source, high-performance chatbot framework that supports speech synthesis, multimodal, and extensible Function Call plugin system. Supports one-click free deployment of your private ChatGPT/LLM web application.
Mastering-GitHub-Copilot-for-Paired-Programming
A 6 Lesson course teaching everything you need to know about harnessing GitHub Copilot and an AI Paired Programing resource.
multi-lora-fine-tune
Provide efficient LLM LoRA fine tune
QAnything
Question and Answer based on Anything.
SadTalker
[CVPR 2023] SadTalker:Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation
super-gradients
Easily train or fine-tune SOTA computer vision models with one open source training library. The home of Yolo-NAS.
vis_dec_neurips
Official Implementation for NeurIPS'23 paper Contrast, Attend and Diffuse to Decode High-Resolution Images from Brain Activities
whisper_dictation
Fast! Offline, privacy-focused, hands-free voice typing, 2-way AI voice chat, with images, voice control, in under 4 GiB of VRAM.
yolo_tracking
BoxMOT: pluggable SOTA tracking modules for segmentation, object detection and pose estimation models