leuchine

reka-vibe-eval

Multimodal language model benchmark, featuring challenging examples

safe-rlhf

Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback

jukebox

Code for the paper "Jukebox: A Generative Model for Music"

the-pile

pile-cc

diplomacy_cicero

Code for Cicero, an AI agent that plays the game of Diplomacy with open-domain natural language negotiation.

mup

maximal update parametrization (µP)

olm-datasets

Pipeline for pulling and processing online language model pretraining data from the web

data-preparation

Code used for sourcing and cleaning the BigScience ROOTS corpus

huggingface_hub

The official Python client for the Huggingface Hub.

tabular-benchmark

ml-visuals

🎨 ML Visuals contains figures and templates which you can reuse and customize to improve your scientific writing.

nessie

Automatically detect errors in annotated corpora.

dataperf

Data Benchmarking

private-transformers

A codebase that makes differentially private training of transformers easy.

YaLM-100B

Pretrained language model with 100B parameters

bigscience

Central place for the engineering/scaling WG: documentation, SLURM scripts and logs, compute environment and data.

CLIP

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

Megatron-LM

Ongoing research training transformer models at scale

perceiver-pytorch

Implementation of Perceiver, General Perception with Iterative Attention, in Pytorch

snorkel

A system for quickly generating training data with weak supervision

CausalMediationAnalysis

Code for the paper "Causal Mediation Analysis for Interpreting Neural NLP: The Case of Gender Bias"

openai-python

The official Python library for the OpenAI API

cleanlab

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

speechbrain

A PyTorch-based Speech Toolkit

gpt-neox

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

fairscale

PyTorch extensions for high performance and large scale training.

spinningup

An educational resource to help anyone learn deep reinforcement learning.

NL-Augmenter

NL-Augmenter 🦎 → 🐍 A Collaborative Repository of Natural Language Transformations

gold-off-policy-text-gen-iclr21