jstjohn

ml-4m

4M: Massively Multimodal Masked Modeling

LLM101n

LLM101n: Let's build a Storyteller

ChannelViT

Channel Vision Transformers: An Image Is Worth C x 16 x 16 Words

mup

maximal update parametrization (µP)

mutransformers

some common Huggingface transformers in maximal update parametrization (µP)

mamba

Mamba SSM architecture

Tranception

Official repository for the paper "Tranception: Protein Fitness Prediction with Autoregressive Transformers and Inference-time Retrieval"

the-algorithm-ml

Source code for Twitter's Recommendation Algorithm

OpenAttack

An Open-Source Package for Textual Adversarial Attack.

mm-cot

Official implementation for "Multimodal Chain-of-Thought Reasoning in Language Models" (stay tuned and more will be updated)

Open-Assistant

OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.

tuning_playbook

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

KendallWeightedDistance

Code repository for computation of Kendall's weighted distance

rgn2

dowhy

DoWhy is a Python library for causal inference that supports explicit modeling and testing of causal assumptions. DoWhy is based on a unified language for causal inference, combining causal graphical models and potential outcomes frameworks.

insertion-deletion-ddpm

Implementation of Insertion-deletion Denoising Diffusion Probabilistic Models

jaxopt

Hardware accelerated, batchable and differentiable optimizers in JAX.

set_transformer

Pytorch implementation of set transformer

theseus

A library for differentiable nonlinear optimization

d2l-en

Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 500 universities from 70 countries including Stanford, MIT, Harvard, and Cambridge.

openfold

Trainable, memory-efficient, and GPU-friendly PyTorch reproduction of AlphaFold 2

paxml

Pax is a Jax-based machine learning framework for training large scale models. Pax allows for advanced and fully configurable experimentation and parallelization, and has demonstrated industry leading model flop utilization rates.

imagen-pytorch

Implementation of Imagen, Google's Text-to-Image Neural Network, in Pytorch

attention_with_linear_biases

Code for the ALiBi method for transformer language models (ICLR 2022)

gpt-neox

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

enformer-tensorflow-sonnet-training-script

The full training script for Enformer - Tensorflow Sonnet

latent-diffusion

High-Resolution Image Synthesis with Latent Diffusion Models

DALLE2-pytorch

Implementation of DALL-E 2, OpenAI's updated text-to-image synthesis neural network, in Pytorch

enformer-pytorch

Implementation of Enformer, Deepmind's attention network for predicting gene expression, in Pytorch

fairseq

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