blankWorld

aicover

ai cover generator

AnomalyCLIP

Official implementation for AnomalyCLIP (ICLR 2024)

Awesome-Quant-Machine-Learning-Trading

Quant/Algorithm trading resources with an emphasis on Machine Learning

backtrader

Python Backtesting library for trading strategies

BYOL-PyTorch

PyTorch implementation of "Bootstrap Your Own Latent: A New Approach to Self-Supervised Learning" with DDP and Apex AMP

ColossalAI

Making large AI models cheaper, faster and more accessible

ControlNet

Let us control diffusion models!

dino

PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO

generative-models

Generative Models by Stability AI

GFPGAN

GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.

GPT-SoVITS

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

gpt4free

The official gpt4free repository | various collection of powerful language models

gpt_academic

为GPT/GLM等LLM大语言模型提供实用化交互接口，特别优化论文阅读/润色/写作体验，模块化设计，支持自定义快捷按钮&函数插件，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, moss等。

hello-algo

《Hello 算法》：动画图解、一键运行的数据结构与算法教程，支持 Python, C++, Java, C#, Go, Swift, JS, TS, Dart, Rust, C, Zig 等语言。English edition ongoing

HelloGitHub

:octocat: 分享 GitHub 上有趣、入门级的开源项目。Share interesting, entry-level open source projects on GitHub.

kornia

Open Source Differentiable Computer Vision Library for PyTorch

LLaMA-Factory

Unify Efficient Fine-Tuning of 100+ LLMs

llama.cpp

LLM inference in C/C++

LoRA

Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"

LWM

ML-NLP

此项目是机器学习(Machine Learning)、深度学习(Deep Learning)、NLP面试中常考到的知识点和代码实现，也是作为一个算法工程师必会的理论基础知识。

qlib

Qlib is an AI-oriented quantitative investment platform, which aims to realize the potential, empower the research, and create the value of AI technologies in quantitative investment. With Qlib, you can easily try your ideas to create better Quant investment strategies.

Real-ESRGAN

Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.

seamless_communication

Foundational Models for State-of-the-Art Speech and Text Translation

stable-diffusion

A latent text-to-image diffusion model

stablediffusion

High-Resolution Image Synthesis with Latent Diffusion Models

unilm

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

vnpy

基于Python的开源量化交易平台开发框架

vnpy_okex

vn.py框架的OKEX交易接口

Yolo-Fastest

:zap: Yolo universal target detection model combined with EfficientNet-lite, the calculation amount is only 230Mflops(0.23Bflops), and the model size is 1.3MB