Official PyTorch Implementation of "SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers"

LLM training in simple, raw C/CUDA

PyTorch code and models for V-JEPA self-supervised learning from video.

PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis

Hyprland is an independent, highly customizable, dynamic tiling Wayland compositor that doesn't sacrifice on its looks.

ChatGPT for Mac, living in your menubar.

GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection

Repository containing all necessary codes to get started on the SoccerNet Tracking challenge. This repository also contains benchmark methods to get started.

[ICCV2023] MixSort: The Customized Tracker in SportsMOT

The official PyTorch implementation of Google's Gemma models

Large World Model With 1M Context

A flexible and efficient codebase for training visually-conditioned language models (VLMs)

Test-time Prompt Tuning (TPT) for zero-shot generalization in vision-language models (NeurIPS 2022))

MixedNUTS: Training-Free Accuracy-Robustness Balance via Nonlinearly Mixed Classifiers

Implementing a ChatGPT-like LLM in PyTorch from scratch, step by step

Code at the speed of thought – Zed is a high-performance, multiplayer code editor from the creators of Atom and Tree-sitter.

VMamba: Visual State Space Models，code is based on mamba

Simple, minimal implementation of the Mamba SSM in one file of PyTorch.

Official pytorch implementation of the paper: "An Edit Friendly DDPM Noise Space: Inversion and Manipulations". CVPR 2024.

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

AirLLM 70B inference with single 4GB GPU

SSH3: faster and rich secure shell using HTTP/3, checkout our article here: https://arxiv.org/abs/2312.08396 and our Internet-Draft: https://datatracker.ietf.org/doc/draft-michel-ssh3/

Official Pytorch Implementation of Paper "A Semantic Space is Worth 256 Language Descriptions: Make Stronger Segmentation Models with Descriptive Properties"

a state-of-the-art-level open visual language model | 多模态预训练模型

A VM with adaptive optimization and JIT compilation, built for Rakudo

Set-of-Mark Prompting for GPT-4V and LMMs

An innovative superfamily of fonts for code

Code for paper "On the Generalization Properties of Diffusion Models"