🤗 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.

Robust Speech Recognition via Large-Scale Weak Supervision

Python tool for converting files and office documents to Markdown.

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

High-Resolution Image Synthesis with Latent Diffusion Models

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

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

A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training

Build resilient language agents as graphs.

🦉 OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation

State-of-the-Art Text Embeddings

Datasets, Transforms and Models specific to Computer Vision

StyleGAN - Official TensorFlow Implementation

Convert Machine Learning Code Between Frameworks

Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"

A framework for training and evaluating AI models on a variety of openly available dialogue datasets.

A framework to enable multimodal models to operate a computer.

Distributed Asynchronous Hyperparameter Optimization in Python

Track-Anything is a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything, XMem, and E2FGVI.

Official PyTorch implementation of StyleGAN3

Distilled variant of Whisper for speech recognition. 6x faster, 50% smaller, within 1% word error rate.

LLM as a Chatbot Service

Kaggle Python docker image

Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Flax.

Joint Detection and Embedding for fast multi-object tracking

Large-scale pretraining for dialogue

Minimalistic large language model 3D-parallelism training

A python tool for evaluating the quality of sentence embeddings.

PyTorch Tutorials from my YouTube channel

Live Speech Portraits: Real-Time Photorealistic Talking-Head Animation (SIGGRAPH Asia 2021)