CarperAI

trlx

A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)

OpenELM

Evolution Through Large Models

cheese

Used for adaptive human in the loop evaluation of language and embedding models.

DRLX

Diffusion Reinforcement Learning Library

Code-Pile

This repository contains all the code for collecting large scale amounts of code from GitHub.

autocrit

A repository for transformer critique learning and generation

InstructGPT

For experiments involving instruct gpt. Currently used for documenting open research questions.

squeakily

A library for squeakily cleaning and filtering language datasets.

Algorithm-Distillation-RLHF

decontamination

This repository contains code for cleaning your training data of benchmark data to help combat data snooping.

treasure_trove

nmmo-environment

Neural MMO - A Massively Multiagent Environment for Artificial Intelligence Research

CodeReviewSE

Stuff related to scraping the Code Review StackExchange

pilev2

magicarp-v2

magiCARP is an API used for crossencoder training.

ArchitextRL

Polygraph

RLHF Mechanistic Interpretability and Deception

nmmo-baselines

Baselines for Neural MMO -- new users should treat this repo as a starter project

FastChat

An open platform for training, serving, and evaluating large language model based chatbots.

AutoPaperclipMaximizer

👀

data-preparation

Code used for sourcing and cleaning the BigScience ROOTS corpus

contriever

Contriever: Unsupervised Dense Information Retrieval with Contrastive Learning

diversity_metrics

sft

goosebox

sandboxed eval server for running code snippets

maxtext

A simple, performant and scalable Jax LLM!

tinypar