will-thompson-k

trax

Trax — Deep Learning with Clear Code and Speed

go-ethereum

Go implementation of the Ethereum protocol

NeuralCompression

A collection of tools for neural compression enthusiasts.

Style-Transfer-in-Text

Paper List for Style Transfer in Text

alphafold

Open source code for AlphaFold.

cvxpy

A Python-embedded modeling language for convex optimization problems.

DALL-E

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

ML-notes

notes about machine learning

Multi-Horizon-Forecasting-for-Limit-Order-Books

lightseq

LightSeq: A High Performance Library for Sequence Processing and Generation

LM-BFF

[ACL 2021] LM-BFF: Better Few-shot Fine-tuning of Language Models https://arxiv.org/abs/2012.15723

style-transformer

dl3d-seminar

Course webpage for COMP 790, (Deep) Learning from Limited Labeled Data

tanl

Structured Prediction as Translation between Augmented Natural Languages

mesh-transformer-jax

Model parallel transformers in JAX and Haiku

gpt-neo

An implementation of model parallel GPT-2 and GPT-3-style models using the mesh-tensorflow library.

CLIP

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

pyprobml

Python code for "Probabilistic Machine learning" book by Kevin Murphy

adapters

A Unified Library for Parameter-Efficient and Modular Transfer Learning

AugLy

A data augmentations library for audio, image, text, and video.

nn_pruning

Prune a model while finetuning or training.

tune

lm-evaluation-harness

A framework for few-shot evaluation of language models.

tokenizers

💥 Fast State-of-the-Art Tokenizers optimized for Research and Production

byt5

seqio

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

robustness-gym

Robustness Gym is an evaluation toolkit for machine learning.

cleanlab

The standard data-centric AI package for data quality and machine learning with messy, real-world data and labels.

pyro

Deep universal probabilistic programming with Python and PyTorch

cryptos

Pure Python from-scratch zero-dependency implementation of Bitcoin for educational purposes