Skip to content

@CarperAI CarperAI

Change the repository type filter

All

    Repositories list

    27 repositories

    • nmmo-baselines

      Public
      Baselines for Neural MMO -- new users should treat this repo as a starter project
      Python
      •
      MIT License
      •39•5•0•1•Updated Nov 26, 2024Nov 26, 2024

    • nmmo-environment

      Public
      Neural MMO - A Massively Multiagent Environment for Artificial Intelligence Research
      Python
      •
      MIT License
      •263•15•0•0•Updated May 30, 2024May 30, 2024

    • DRLX

      Public
      Diffusion Reinforcement Learning Library
      Python
      •
      MIT License
      •7•174•8•1•Updated Feb 13, 2024Feb 13, 2024

    • trlx

      Public
      A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)
      machine-learningreinforcement-learningpytorch
      Python
      •
      MIT License
      •470•4.5k•79•15•Updated Jan 8, 2024Jan 8, 2024

    • autocrit

      Public
      A repository for transformer critique learning and generation
      Python
      •17•85•3•3•Updated Dec 7, 2023Dec 7, 2023

    • OpenELM

      Public
      Evolution Through Large Models
      Python
      •
      MIT License
      •86•696•6•1•Updated Nov 15, 2023Nov 15, 2023

    • treasure_trove

      Public
      Jupyter Notebook
      •
      Apache License 2.0
      •5•22•0•1•Updated Aug 27, 2023Aug 27, 2023

    • diversity_metrics

      Public
      Jupyter Notebook
      •0•1•0•0•Updated Aug 10, 2023Aug 10, 2023

    • magicarp-v2

      Public
      magiCARP is an API used for crossencoder training.
      Python
      •3•10•4•0•Updated Jul 27, 2023Jul 27, 2023

    • tinypar

      Public
      Python
      •8•0•0•0•Updated Jul 16, 2023Jul 16, 2023

    • Polygraph

      Public
      RLHF Mechanistic Interpretability and Deception
      MIT License
      •1•6•0•0•Updated Jul 14, 2023Jul 14, 2023

    • squeakily

      Public
      A library for squeakily cleaning and filtering language datasets.
      Jupyter Notebook
      •
      Apache License 2.0
      •9•45•2•2•Updated Jul 10, 2023Jul 10, 2023

    • maxtext

      Public
      A simple, performant and scalable Jax LLM!
      Python
      •
      Apache License 2.0
      •297•1•0•0•Updated Jun 30, 2023Jun 30, 2023

    • sft

      Public
      Python
      •3•2•0•1•Updated Jun 29, 2023Jun 29, 2023

    • ArchitextRL

      Public
      Python
      •
      MIT License
      •4•8•0•0•Updated Jun 21, 2023Jun 21, 2023

    • FastChat

      Public
      An open platform for training, serving, and evaluating large language model based chatbots.
      Python
      •
      Apache License 2.0
      •4.6k•4•0•0•Updated Apr 26, 2023Apr 26, 2023

    • decontamination

      Public
      This repository contains code for cleaning your training data of benchmark data to help combat data snooping.
      Jupyter Notebook
      •
      Apache License 2.0
      •3•25•0•0•Updated Apr 21, 2023Apr 21, 2023

    • pilev2

      Public
      Python
      •
      MIT License
      •9•11•1•3•Updated Mar 24, 2023Mar 24, 2023

    • goosebox

      Public
      sandboxed eval server for running code snippets
      MIT License
      •1•1•0•0•Updated Mar 1, 2023Mar 1, 2023

    • cheese

      Public
      Used for adaptive human in the loop evaluation of language and embedding models.
      Python
      •
      MIT License
      •24•304•3•0•Updated Mar 1, 2023Mar 1, 2023

    • Code-Pile

      Public
      This repository contains all the code for collecting large scale amounts of code from GitHub.
      dataset
      Python
      •
      MIT License
      •29•105•18•4•Updated Feb 17, 2023Feb 17, 2023

    • Algorithm-Distillation-RLHF

      Public
      Python
      •
      MIT License
      •5•34•1•3•Updated Jan 29, 2023Jan 29, 2023

    • CodeReviewSE

      Public
      Stuff related to scraping the Code Review StackExchange
      Python
      •5•11•0•1•Updated Jan 19, 2023Jan 19, 2023

    • InstructGPT

      Public
      For experiments involving instruct gpt. Currently used for documenting open research questions.
      MIT License
      •3•71•25•0•Updated Nov 8, 2022Nov 8, 2022

    • data-preparation

      Public
      Code used for sourcing and cleaning the BigScience ROOTS corpus
      E
      •
      Apache License 2.0
      •41•4•0•0•Updated Nov 6, 2022Nov 6, 2022

    • AutoPaperclipMaximizer

      Public
      👀
      MIT License
      •0•3•2•0•Updated Oct 7, 2022Oct 7, 2022

    • contriever

      Public
      Contriever: Unsupervised Dense Information Retrieval with Contrastive Learning
      Python
      •
      Other
      •60•2•0•0•Updated Jul 28, 2022Jul 28, 2022