Skip to content

@AlignmentResearch FAR.AI

Change the repository type filter

All

    Repositories list

    52 repositories

    • mlflow

      Public
      Open source platform for the machine learning lifecycle
      Python
      •
      Apache License 2.0
      •4.8k•0•0•3•Updated Aug 7, 2025Aug 7, 2025

    • tuned-lens

      Public
      Tools for understanding how transformer predictions are built layer-by-layer
      machine-learningtransformerspytorch
      Python
      •
      MIT License
      •57•513•13•4•Updated Aug 7, 2025Aug 7, 2025

    • trl

      Public
      Train transformer language models with reinforcement learning.
      Python
      •
      Apache License 2.0
      •2.1k•0•0•1•Updated Aug 4, 2025Aug 4, 2025

    • cupbearer

      Public
      A library for mechanistic anomaly detection
      Python
      •
      MIT License
      •11•0•0•0•Updated Aug 4, 2025Aug 4, 2025

    • DeepGEMM

      Public
      DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling
      Cuda
      •
      MIT License
      •669•0•0•0•Updated Jul 25, 2025Jul 25, 2025

    • deception-evasion-honesty

      Public
      Python
      •2•1•1•1•Updated Jul 22, 2025Jul 22, 2025

    • harmtune

      Public
      Python
      •0•6•2•0•Updated Jul 8, 2025Jul 8, 2025

    • AttemptPersuadeEval

      Public
      Python
      •
      Apache License 2.0
      •0•3•1•0•Updated Jul 4, 2025Jul 4, 2025

    • aim

      Public
      Aim 💫 — An easy-to-use & supercharged open-source experiment tracker.
      Python
      •
      Apache License 2.0
      •350•0•0•2•Updated Jul 3, 2025Jul 3, 2025

    • entangled.py

      Public
      Python port of Entangled
      Python
      •
      Apache License 2.0
      •10•0•0•0•Updated Jun 30, 2025Jun 30, 2025

    • learned-planner

      Public
      Interpreting Learned Search and Planning: Reverse-engineering recurrent convolutional networks (DRC) that play Sokoban
      Python
      •
      Apache License 2.0
      •5•14•1•0•Updated Jun 29, 2025Jun 29, 2025

    • defense-in-depth-demo

      Public
      Python
      •
      MIT License
      •0•2•0•0•Updated Jun 28, 2025Jun 28, 2025

    • train-learned-planner

      Public
      Experimenting with CleanRL for learned-planners
      Python
      •
      Other
      •1•7•1•1•Updated Jun 16, 2025Jun 16, 2025

    • HarmBench

      Public
      Fork of HarmBench for getting R2D2 working
      Jupyter Notebook
      •
      MIT License
      •106•0•0•0•Updated Jun 14, 2025Jun 14, 2025

    • voltage-park-sdk

      Public
      Python
      •
      BSD 3-Clause "New" or "Revised" License
      •0•0•0•0•Updated Jun 6, 2025Jun 6, 2025

    • scaling-llm-robustness-paper

      Public
      Code used for the paper `Scaling Trends in Language Model Robustness`
      Python
      •
      MIT License
      •0•0•0•0•Updated Jun 4, 2025Jun 4, 2025

    • emergent-misalignment

      Public
      Python
      •
      MIT License
      •58•0•0•0•Updated Jun 3, 2025Jun 3, 2025

    • safety-gap

      Public
      Python
      •0•1•1•0•Updated May 30, 2025May 30, 2025

    • gcg

      Public
      Fork of official GCG repo
      Python
      •
      MIT License
      •552•0•0•0•Updated May 30, 2025May 30, 2025

    • kueue

      Public
      Kubernetes-native Job Queueing
      Go
      •
      Apache License 2.0
      •386•0•0•1•Updated May 28, 2025May 28, 2025

    • kubespray

      Public
      Deploy a Production Ready Kubernetes Cluster
      Jinja
      •
      Apache License 2.0
      •6.7k•0•0•0•Updated Apr 23, 2025Apr 23, 2025

    • s3bucket_exporter

      Public
      S3 bucket exporter exposing metrics size and number of objects
      Go
      •
      MIT License
      •12•0•0•0•Updated Apr 21, 2025Apr 21, 2025

    • alignment-workshop-website

      Public
      Stub website for redirects to new FAR.AI website
      0•0•0•0•Updated Apr 14, 2025Apr 14, 2025

    • envpool

      Public
      C++-based high-performance parallel environment execution engine (vectorized env) for general RL environments.
      C++
      •
      Apache License 2.0
      •114•2•0•1•Updated Apr 8, 2025Apr 8, 2025

    • learned-planners-stable-baselines3

      Public
      PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
      Python
      •
      MIT License
      •1.9k•3•0•0•Updated Apr 2, 2025Apr 2, 2025

    • gym-sokoban

      Public
      Sokoban environment for Gym
      Python
      •
      MIT License
      •0•0•0•0•Updated Apr 2, 2025Apr 2, 2025

    • refusal_direction

      Public
      Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".
      Python
      •
      Apache License 2.0
      •64•1•0•0•Updated Mar 19, 2025Mar 19, 2025

    • KataGoVisualizer

      Public
      HTML
      •
      MIT License
      •1•3•6•0•Updated Mar 1, 2025Mar 1, 2025

    • alpaca_eval

      Public
      Jupyter Notebook
      •
      Apache License 2.0
      •284•0•0•0•Updated Feb 13, 2025Feb 13, 2025

    • oauth2-proxy-buildpack

      Public
      Fork of https://github.com/cfra/heroku-buildpack-oauth2-proxy for internal use
      Shell
      •
      Apache License 2.0
      •0•0•0•0•Updated Jan 27, 2025Jan 27, 2025