CarperAI ORG

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

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

Evolution Through Large Models

Diffusion Reinforcement Learning Library

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

A repository for transformer critique learning and generation

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

A library for squeakily cleaning and filtering language datasets.

No description.

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

No description.

Neural MMO - A Massively Multiagent Environment for Artificial Intelligence Research

Stuff related to scraping the Code Review StackExchange

No description.

magiCARP is an API used for crossencoder training.

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

No description.

RLHF Mechanistic Interpretability and Deception

Code used for sourcing and cleaning the BigScience ROOTS corpus

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

👀

No description.

Contriever: Unsupervised Dense Information Retrieval with Contrastive Learning

A simple, performant and scalable Jax LLM!

No description.

sandboxed eval server for running code snippets

No description.