uranusx86

gim

GIM: Learning Generalizable Image Matcher From Internet Videos (ICLR 2024 Spotlight)

Chinese-Mixtral

中文Mixtral混合专家大模型（Chinese Mixtral MoE LLMs）

Chinese-LLaMA-Alpaca-3

中文羊驼大模型三期项目 (Chinese Llama-3 LLMs) developed from Meta Llama 3

AniPortrait

AniPortrait: Audio-Driven Synthesis of Photorealistic Portrait Animation

MusePose

MusePose: a Pose-Driven Image-to-Video Framework for Virtual Human Generation

MuseTalk

MuseTalk: Real-Time High Quality Lip Synchorization with Latent Space Inpainting

electra

ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators

gosu

Simple Go-based setuid+setgid+setgroups+exec

whisper-jax

JAX implementation of OpenAI's Whisper model for up to 70x speed-up on TPU.

iansui

芫荽，基於 Klee One 改造的學習用台灣繁體字型

how-to-optimize-gemm

TensorRT-LLM

TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.

nnfusion

A flexible and efficient deep neural network (DNN) compiler that generates high-performance executable from a DNN model description.

All-Age-Faces-Dataset

All-Age-Faces (AAF) Database.

SpinKit

A collection of loading indicators animated with CSS

rome

Realistic mesh-based avatars. ECCV 2022

roop

one-click face swap

talking-head-anime-3-demo

Demo Programs for the "Talking Head(?) Anime from a Single Image 3: Now the Body Too" Project

DeepFaceLive

Real-time face swap for PC streaming or video calls

fonts

Patched fonts for Powerline users.

nodriver

Successor of Undetected-Chromedriver. Providing a blazing fast framework for web automation, webscraping, bots and any other creative ideas which are normally hindered by annoying anti bot systems like Captcha / CloudFlare / Imperva / hCaptcha

tixcraft_bot

MaxBot open source code bot

qdrant

Qdrant - High-performance, massive-scale Vector Database for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/

faiss

A library for efficient similarity search and clustering of dense vectors.

LLMLingua

To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.

SOLIDER

A Semantic Controllable Self-Supervised Learning Framework to learn general human representations from massive unlabeled human images, which can benefit downstream human-centric tasks to the maximum extent

pyreft

ReFT: Representation Finetuning for Language Models

llm.c

LLM training in simple, raw C/CUDA

adapters

A Unified Library for Parameter-Efficient and Modular Transfer Learning

transformer-heads

Toolkit for attaching, training, saving and loading of new heads for transformer models