zanussbaum

gpt4all.cpp

Locally run an Assistant-Tuned Chat-Style LLM

pluribus

An attempt at a Python implementation of Pluribus, a No-Limits Hold'em Poker Bot

accelerate

🚀 A simple way to train and use PyTorch models with multi-GPU, TPU, mixed-precision

bert-movie-rec

mup-tf

Maximal Update Parameterization in Tensorflow

BERT4Rec-VAE-Pytorch

Pytorch implementation of BERT4Rec and Netflix VAE.

contracts

contracts

datasets

🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools

doccano

Open source annotation tool for machine learning practitioners.

dotfiles

enformer-tensorflow-sonnet-training-script

The full training script for Enformer - Tensorflow Sonnet

flax-sentence-embeddings

Shared code for training sentence embeddings with Flax / JAX

img2dataset

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

llama_index

LlamaIndex (formerly GPT Index) is a data framework for your LLM applications

lm-evaluation-harness

A framework for few-shot evaluation of autoregressive language models.

LongEmbed

Official implementation for the paper "LongEmbed: Extending Embedding Models for Long Context Retrieval"

ludwig

Ludwig is a toolbox that allows to train and evaluate deep learning models without the need to write code.

mlx_embedding_models

run embeddings in MLX

mup

maximal update parametrization (µP)

nodelist-inflator

CLI tool to easily expand a list of hostnames (which include brackets) and write to a hosttile

nyc-test-tracker

peft

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

pyGAT

Pytorch implementation of the Graph Attention Network model by Veličković et. al (2017, https://arxiv.org/abs/1710.10903)

pyserini

Pyserini is a Python toolkit for reproducible information retrieval research with sparse and dense representations.

s3fs

S3 Filesystem

session_based_recommenders

Official repo for FF19: Session-based Recommender Systems

snorkel

A system for quickly generating training data with weak supervision

transformers

🤗Transformers: State-of-the-art Natural Language Processing for Pytorch and TensorFlow 2.0.

Transformers4Rec

Transformers4Rec is a flexible and efficient library for sequential and session-based recommendation, available for both PyTorch and Tensorflow.

vec2text

utilities for decoding deep representations (like sentence embeddings) back to text