Vane is an AI-powered answering engine.

OmniGen: Unified Image Generation. https://arxiv.org/pdf/2409.11340

A guidance language for controlling large language models.

Implementation of Nougat Neural Optical Understanding for Academic Documents

🧑‍🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), ga…

Python bindings for the Transformer models implemented in C/C++ using GGML library.

200+ detailed flashcards useful for reviewing topics in machine learning, computer vision, and computer science.

torch-optimizer -- collection of optimizers for Pytorch

Machine learning, in numpy

Taming Transformers for High-Resolution Image Synthesis

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

A hyperparameter optimization framework

Official Implementation of 'Fast AutoAugment' in PyTorch.

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…

Fast, general, and tested differentiable structured prediction in PyTorch

Python Fire is a library for automatically generating command line interfaces (CLIs) from absolutely any Python object.

A curated list of resources dedicated to text summarization

Tools to Design or Visualize Architecture of Neural Network

Repository to track the progress in Natural Language Processing (NLP), including the datasets and the current state-of-the-art for the most common NLP tasks.

Build, Manage and Deploy AI/ML Systems

List of useful data augmentation resources. You will find here some not common techniques, libraries, links to GitHub repos, papers, and others.

A lightweight library for converting complex objects to and from simple Python datatypes.

A scikit-learn compatible neural network library that wraps PyTorch

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

Machine learning tools in JavaScript

Jupyter magics and kernels for working with remote Spark clusters

Modin: Scale your Pandas workflows by changing a single line of code

A collection of various deep learning architectures, models, and tips

Python package to easily retrain OpenAI's GPT-2 text-generating model on new texts