Lists (4)
Stars
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
The simplest, fastest repository for training/finetuning medium-sized GPTs.
The definitive Web UI for local AI, with powerful features and easy setup.
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
We write your reusable computer vision tools. 💜
If you live in the terminal, kitty is made for you! Cross-platform, fast, feature-rich, GPU based.
HunyuanVideo: A Systematic Framework For Large Video Generation Model
The AI developer platform. Use Weights & Biases to train and fine-tune models, and manage models from experimentation to production.
Refine high-quality datasets and visual AI models
Hydra is a framework for elegantly configuring complex applications
High-Resolution 3D Human Digitization from A Single Image.
GLM-130B: An Open Bilingual Pre-Trained Model (ICLR 2023)
Track-Anything is a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything, XMem, and E2FGVI.
A concise but complete full-attention transformer with a set of promising experimental features from various papers
PyTorch Lightning + Hydra. A very user-friendly template for ML experimentation. ⚡🔥⚡
The official PyTorch implementation of the paper "Human Motion Diffusion Model"
Official implementation of CVPR2020 paper "VIBE: Video Inference for Human Body Pose and Shape Estimation"
Code for visualizing the loss landscape of neural nets
Code and dataset for photorealistic Codec Avatars driven from audio
SkyReels V1: The first and most advanced open-source human-centric video foundation model
Flexible Python configuration system. The last one you will ever need.
Expressive Body Capture: 3D Hands, Face, and Body from a Single Image
The official repo for [NeurIPS'22] "ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation" and [TPAMI'23] "ViTPose++: Vision Transformer for Generic Body Pose Estimation"
A pipeline parallel training script for diffusion models.
An end-to-end library for editing and rendering motion of 3D characters with deep learning [SIGGRAPH 2020]
A fast, efficient universal vector embedding utility package.