carperai Goto Github PK

algorithm-distillation-rlhf

architextrl

autocrit

A repository for transformer critique learning and generation

autopaperclipmaximizer

👀

cheese

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

code-pile

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

codereviewse

Stuff related to scraping the Code Review StackExchange

contriever

Contriever: Unsupervised Dense Information Retrieval with Contrastive Learning

data-preparation

Code used for sourcing and cleaning the BigScience ROOTS corpus

decontamination

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

diversity_metrics

drlx

Diffusion Reinforcement Learning Library

fastchat

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

goosebox

sandboxed eval server for running code snippets

instructgpt

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

magicarp-v2

magiCARP is an API used for crossencoder training.

maxtext

A simple, performant and scalable Jax LLM!

nmmo-baselines

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

nmmo-environment

Neural MMO - A Massively Multiagent Environment for Artificial Intelligence Research

openelm

Evolution Through Large Models

pilev2

polygraph

RLHF Mechanistic Interpretability and Deception

sft

squeakily

A library for squeakily cleaning and filtering language datasets.

tinypar

treasure_trove

trlx

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