Skip to content

@AlignmentResearch FAR.AI

Change the repository type filter

All

    Repositories list

    28 repositories

    • scaling-poisoning

      Public
      Python
      •0•1•0•2•Updated Oct 3, 2024Oct 3, 2024

    • gym-sokoban

      Public
      Sokoban environment for Gym
      Python
      •
      MIT License
      •0•0•0•1•Updated Oct 1, 2024Oct 1, 2024

    • KataGoVisualizer

      Public
      HTML
      •
      MIT License
      •1•3•6•0•Updated Sep 24, 2024Sep 24, 2024

    • go_attack

      Public
      Python
      •
      MIT License
      •7•79•12•0•Updated Sep 24, 2024Sep 24, 2024

    • lp_sae

      Public
      Training Sparse Autoencoders on DRC networks
      HTML
      •
      MIT License
      •107•0•0•1•Updated Sep 12, 2024Sep 12, 2024

    • envpool

      Public
      C++-based high-performance parallel environment execution engine (vectorized env) for general RL environments.
      C++
      •
      Apache License 2.0
      •99•0•0•1•Updated Aug 21, 2024Aug 21, 2024

    • train-learned-planner

      Public
      Experimenting with CleanRL for learned-planners
      Python
      •
      Other
      •0•3•0•1•Updated Aug 21, 2024Aug 21, 2024

    • KataGo-custom

      Public
      Child repository of https://github.com/HumanCompatibleAI/go_attack.
      C++
      •
      Other
      •1•4•6•0•Updated Aug 14, 2024Aug 14, 2024

    • learned-planner

      Public
      Interp tools for recurrent networks that play Sokoban
      Python
      •
      Apache License 2.0
      •1•6•1•0•Updated Aug 2, 2024Aug 2, 2024

    • learned-planners-stable-baselines3

      Public
      PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
      Python
      •
      MIT License
      •1.7k•2•0•0•Updated Jun 27, 2024Jun 27, 2024

    • vlmrm

      Public
      Python
      •
      MIT License
      •11•37•2•0•Updated Jun 25, 2024Jun 25, 2024

    • sae-k-sparse-mamba

      Public
      K-Sparse Autoencoders for Mamba
      Python
      •
      MIT License
      •40•1•0•0•Updated Jun 20, 2024Jun 20, 2024

    • tuned-lens

      Public
      Tools for understanding how transformer predictions are built layer-by-layer
      machine-learningtransformerspytorch
      Python
      •
      MIT License
      •44•412•10•1•Updated Jun 2, 2024Jun 2, 2024

    • farconf

      Public
      Easy dataclass-based configuration for ML projects
      Python
      •0•1•0•0•Updated May 23, 2024May 23, 2024

    • kueue

      Public
      Kubernetes-native Job Queueing
      Go
      •
      Apache License 2.0
      •238•0•0•0•Updated Apr 30, 2024Apr 30, 2024

    • stable-baselines3

      Public
      PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
      Python
      •
      MIT License
      •1.7k•1•0•0•Updated Mar 16, 2024Mar 16, 2024

    • mats_sae_training

      Public
      Training Sparse Autoencoders on Language Models
      Python
      •
      MIT License
      •107•2•0•0•Updated Mar 1, 2024Mar 1, 2024

    • MambaLens

      Public
      Mamba support for transformer lens
      Python
      •
      MIT License
      •3•0•0•0•Updated Feb 26, 2024Feb 26, 2024

    • gpt-4-novel-apis-attacks

      Public
      1•17•0•0•Updated Dec 28, 2023Dec 28, 2023

    • SimpleParsing

      Public
      Simple, Elegant, Typed Argument Parsing with argparse
      Python
      •
      MIT License
      •52•0•0•0•Updated Nov 6, 2023Nov 6, 2023

    • alpaca-lora

      Public
      Instruct-tune LLaMA on consumer hardware
      Jupyter Notebook
      •
      Apache License 2.0
      •2.2k•1•0•0•Updated Jul 5, 2023Jul 5, 2023

    • polygames

      Public
      C++
      •
      MIT License
      •53•0•8•0•Updated Jun 20, 2023Jun 20, 2023

    • pgx

      Public
      A collection of highly-parallel RL game environments written in JAX
      Python
      •
      Apache License 2.0
      •25•1•0•0•Updated Apr 27, 2023Apr 27, 2023

    • epic

      Public
      Implements the Equivalent-Policy Invariant Comparison (EPIC) distance for reward functions.
      Python
      •
      MIT License
      •3•2•2•1•Updated Feb 1, 2023Feb 1, 2023

    • leela-zero

      Public
      Go engine with no human-provided knowledge, modeled after the AlphaGo Zero paper.
      C++
      •
      GNU General Public License v3.0
      •1k•0•0•0•Updated Jan 18, 2023Jan 18, 2023

    • magicwormhole-docker

      Public
      Dockerfile for Magic Wormhole
      Dockerfile
      •
      MIT License
      •0•1•0•0•Updated Oct 11, 2022Oct 11, 2022

    • gogui

      Public
      Graphical user interface for the game of Go, and other similar board games
      Java
      •
      Other
      •21•1•0•0•Updated Oct 8, 2022Oct 8, 2022

    • ELF

      Public
      ELF: a platform for game research with AlphaGoZero/AlphaZero reimplementation
      C++
      •
      Other
      •567•0•0•0•Updated Oct 7, 2022Oct 7, 2022