Ungreedy subword tokenizer and vocabulary trainer for Python, Go & Javascript

An implementation of model parallel autoregressive transformers on GPUs, based on the Megatron and DeepSpeed libraries

Development repository for the Triton language and compiler

MoVQGAN - model for the image encoding and reconstruction

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

A repository for research on medium sized language models.

Easily compute clip embeddings from video frames

Mentat - The AI Coding Assistant

commaVQ is a dataset of compressed driving video

Easily create large video dataset from video urls

LLM inference in C/C++

Train vision models using JAX and 🤗 transformers

Supercharge Your Model Training

Story-Based Retrieval with Contextual Embeddings. Largest freely available movie video dataset. [ACCV'20]

Official repo for consistency models.

You like pytorch? You like micrograd? You love tinygrad! ❤️

A feature-rich command-line audio/video downloader

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

CLIP-like model evaluation

An open-source framework for training large multimodal models.

Easily convert common crawl to a dataset of caption and document. Image/text Audio/text Video/text, ...

A curated list of deep learning resources for video-text retrieval.

Simple python template

Large-scale text-video dataset. 10 million captioned short videos.

gpu tester detects broken and slow gpus in a cluster

Reinforcement learning library

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

Efficiently read embedding in streaming from any filesystem