Skip to content

@allenai Ai2

Change the repository type filter

All

    Repositories list

    534 repositories

    • OLMo-core

      Public
      PyTorch building blocks for the OLMo ecosystem
      Python
      •
      Apache License 2.0
      •92•522•7•40•Updated Dec 10, 2025Dec 10, 2025

    • olmoearth_projects

      Public
      OlmoEarth projects
      Python
      •
      Other
      •5•45•1•2•Updated Dec 10, 2025Dec 10, 2025

    • rslearn

      Public
      A tool for developing remote sensing datasets and models.
      Python
      •
      Apache License 2.0
      •10•59•20•3•Updated Dec 10, 2025Dec 10, 2025

    • open-instruct

      Public
      AllenAI's post-training codebase
      Python
      •
      Apache License 2.0
      •471•3.4k•11•44•Updated Dec 10, 2025Dec 10, 2025

    • olmo-cookbook

      Public
      OLMost every training recipe you need to perform data interventions with the OLMo family of models.
      Python
      •
      Apache License 2.0
      •11•57•1•31•Updated Dec 10, 2025Dec 10, 2025

    • olmocr

      Public
      Toolkit for linearizing PDFs for LLM datasets/training
      Python
      •
      Apache License 2.0
      •1.2k•16k•31•13•Updated Dec 9, 2025Dec 9, 2025

    • PeerRead

      Public
      Data and code for Kang et al., NAACL 2018's paper titled "A Dataset of Peer Reviews (PeerRead): Collection, Insights and NLP Applications"
      Python
      •108•424•5•3•Updated Dec 9, 2025Dec 9, 2025

    • dnw

      Public
      Discovering Neural Wirings (https://arxiv.org/abs/1906.00586)
      machine-learningcomputer-visionneural-networks
      Python
      •
      Other
      •17•136•2•6•Updated Dec 9, 2025Dec 9, 2025

    • hidden-networks

      Public
      Python
      •
      Apache License 2.0
      •54•193•2•5•Updated Dec 9, 2025Dec 9, 2025

    • savn

      Public
      Learning to Learn how to Learn: Self-Adaptive Visual Navigation using Meta-Learning (https://arxiv.org/abs/1812.00971)
      reinforcement-learningself-adaptivemeta-learningai2thor-environment
      Python
      •
      Apache License 2.0
      •55•193•19•5•Updated Dec 9, 2025Dec 9, 2025

    • TOPICAL

      Public
      🪄📄 TOPICAL: TOPIC pages AutomagicaLly
      nlpbionlplarge-language-modelsretrieval-augmented-generationtopic-pages
      Python
      •
      Apache License 2.0
      •3•9•2•1•Updated Dec 9, 2025Dec 9, 2025

    • olmoearth_pretrain

      Public
      Earth system foundation model data, training, and eval
      Python
      •
      Other
      •17•113•2•13•Updated Dec 9, 2025Dec 9, 2025

    • rslearn_projects

      Public
      Python
      •
      Apache License 2.0
      •6•16•15•6•Updated Dec 9, 2025Dec 9, 2025

    • duplodocus

      Public
      Tooling for exact and MinHash deduplication of large-scale text datasets
      Rust
      •
      Apache License 2.0
      •3•40•0•1•Updated Dec 9, 2025Dec 9, 2025

    • setup-beaker

      Public
      Set up your GitHub Actions workflow with the Beaker command-line client
      beakergithub-actions
      Python
      •
      Apache License 2.0
      •3•6•0•8•Updated Dec 9, 2025Dec 9, 2025

    • scirepeval

      Public
      SciRepEval benchmark training and evaluation scripts
      Python
      •
      Apache License 2.0
      •13•78•3•1•Updated Dec 8, 2025Dec 8, 2025

    • agent-baselines

      Public
      Python
      •
      Apache License 2.0
      •12•98•1•0•Updated Dec 8, 2025Dec 8, 2025

    • infinigram-api

      Public
      Python
      •
      Apache License 2.0
      •11•87•6•1•Updated Dec 6, 2025Dec 6, 2025

    • molmoact

      Public
      Official Repository for MolmoAct
      Python
      •
      Apache License 2.0
      •28•269•7•1•Updated Dec 6, 2025Dec 6, 2025

    • S2AFF

      Public
      link raw affiliation to ROR ids
      Jupyter Notebook
      •
      Apache License 2.0
      •5•30•6•0•Updated Dec 5, 2025Dec 5, 2025

    • FlexOlmo

      Public
      Code and training scripts for FlexOlmo
      Python
      •
      Apache License 2.0
      •16•117•5•11•Updated Dec 5, 2025Dec 5, 2025

    • atlantes

      Public
      Efficient and low latency real-time global-scale GPS trajectory modeling
      Python
      •14•60•1•6•Updated Dec 5, 2025Dec 5, 2025

    • scispacy

      Public
      A full spaCy pipeline and models for scientific/biomedical documents.
      nlpbioinformaticsspacybiomedicalcustom-pipesscientific-documents
      Python
      •
      Apache License 2.0
      •249•1.9k•35•3•Updated Dec 4, 2025Dec 4, 2025

    • ScienceWorld

      Public
      ScienceWorld is a text-based virtual environment centered around accomplishing tasks from the standardized elementary science curriculum.
      machine-learningreinforcement-learninglanguage-modeltext-based-gametext-based-game-framework
      Scala
      •
      Apache License 2.0
      •32•316•15•0•Updated Dec 3, 2025Dec 3, 2025

    • decon

      Public
      decontamination
      Rust
      •
      Apache License 2.0
      •0•17•0•0•Updated Dec 3, 2025Dec 3, 2025

    • autodiscovery

      Public
      Official code for NeurIPS 2025 paper "AutoDiscovery: Open-ended Scientific Discovery via Bayesian Surprise"
      Python
      •15•109•0•0•Updated Dec 2, 2025Dec 2, 2025

    • dolma3

      Public
      Jupyter Notebook
      •
      Apache License 2.0
      •4•29•0•1•Updated Nov 30, 2025Nov 30, 2025

    • IFBench

      Public
      Python
      •
      Apache License 2.0
      •16•93•0•0•Updated Nov 27, 2025Nov 27, 2025

    • codescientist

      Public
      CodeScientist: An automated scientific discovery system for code-based experiments
      Python
      •
      Apache License 2.0
      •40•303•1•0•Updated Nov 27, 2025Nov 27, 2025

    • panda

      Public
      Panda ("plan-and-act") agent for Autonomous Scientific Discovery
      Python
      •
      Apache License 2.0
      •2•4•0•0•Updated Nov 26, 2025Nov 26, 2025