WIP

A library for unit scaling in PyTorch

Simple implementation of muP, based on Spectral Condition for Feature Learning. The implementation is SGD only, dont use it for Adam

LLM101n: Let's build a Storyteller

DataComp for Language Models

seqax = sequence modeling + JAX

[GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". An *ultra-simple, user-friendly …

This repository provides the code and model checkpoints of the research paper: Scalable Pre-training of Large Autoregressive Image Models

PyTorch Implementation of "V* : Guided Visual Search as a Core Mechanism in Multimodal LLMs"

MLX: An array framework for Apple silicon

PyTorch implementation of RCG https://arxiv.org/abs/2312.03701

An Extensible Deep Learning Library

Task-based datasets, preprocessing, and evaluation for sequence models.

distributed trainer for LLMs

Hackable and optimized Transformers building blocks, supporting a composable construction.

COYO-700M: Large-scale Image-Text Pair Dataset

arXiv LaTeX Cleaner: Easily clean the LaTeX code of your paper to submit to arXiv

Inference code for Llama models

LAVIS - A One-stop Library for Language-Vision Intelligence

A playbook for systematically maximizing the performance of deep learning models.

The simplest, fastest repository for training/finetuning medium-sized GPTs.

Tensors, for human consumption

Official repository of OFA (ICML 2022). Paper: OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework

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

[ICLR2024] Exploring Target Representations for Masked Autoencoders