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

TensorFlow code and pre-trained models for BERT

The official Python library for the OpenAI API

Code for the paper "Language Models are Unsupervised Multitask Learners"

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

Graph Neural Network Library for PyTorch

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

The ChatGPT Retrieval Plugin lets you easily find personal or work documents by asking questions in natural language.

WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)

Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".

Python Implementation of Reinforcement Learning: An Introduction

PyTorch package for the discrete VAE used for DALL·E.

Code for the paper "Jukebox: A Generative Model for Music"

Uniform Manifold Approximation and Projection

Repo for external large-scale work

XLNet: Generalized Autoregressive Pretraining for Language Understanding

[NeurIPS 2023] Official implementation of the paper "Segment Everything Everywhere All at Once"

Sequence modeling benchmarks and temporal convolutional networks

Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.

🦦 Otter, a multi-modal model based on OpenFlamingo (open-sourced version of DeepMind's Flamingo), trained on MIMIC-IT and showcasing improved instruction-following and in-context learning ability.

[ICLR 2020] Contrastive Representation Distillation (CRD), and benchmark of recent knowledge distillation methods

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

Unsupervised Word Segmentation for Neural Machine Translation and Text Generation

Multi-Task Deep Neural Networks for Natural Language Understanding

Open-Set Grounded Text-to-Image Generation

PyTorch implementation of SwAV https//arxiv.org/abs/2006.09882

LSTM and QRNN Language Model Toolkit for PyTorch

Train AI models efficiently on medical images using any framework