Skip to content

@EleutherAI EleutherAI

Change the repository type filter

All

    Repositories list

    150 repositories

    • lm-evaluation-harness

      Public
      A framework for few-shot evaluation of language models.
      transformerlanguage-modelevaluation-framework
      Python
      •
      MIT License
      •1.7k•6.6k•287•91•Updated Oct 5, 2024Oct 5, 2024

    • gpt-neox

      Public
      An implementation of model parallel autoregressive transformers on GPUs, based on the Megatron and DeepSpeed libraries
      transformerslanguage-modelgpt-3deepspeed-library
      Python
      •
      Apache License 2.0
      •996•6.9k•55•21•Updated Oct 3, 2024Oct 3, 2024

    • optax-galore

      Public
      Adds GaLore style projection wrappers to optax optimizers
      Python
      •
      MIT License
      •0•3•0•0•Updated Oct 3, 2024Oct 3, 2024

    • equinox-llama

      Public
      Equinox implementation of llama3 and llama3.1
      Python
      •
      MIT License
      •0•4•0•0•Updated Oct 3, 2024Oct 3, 2024

    • sae-auto-interp

      Public
      Python
      •
      Apache License 2.0
      •7•64•0•0•Updated Oct 3, 2024Oct 3, 2024

    • ngrams-across-time

      Public
      Jupyter Notebook
      •
      MIT License
      •0•1•0•0•Updated Oct 3, 2024Oct 3, 2024

    • cupbearer

      Public
      A library for mechanistic anomaly detection
      Python
      •
      MIT License
      •9•5•0•0•Updated Oct 3, 2024Oct 3, 2024

    • tokengrams

      Public
      Efficiently computing & storing token n-grams from large corpora
      Rust
      •
      MIT License
      •3•15•0•0•Updated Oct 2, 2024Oct 2, 2024

    • sgdensity

      Public
      Computing the implicit probability densities that SGD assigns to networks
      Python
      •
      Apache License 2.0
      •0•0•0•0•Updated Oct 1, 2024Oct 1, 2024

    • semantic-memorization

      Public
      Jupyter Notebook
      •5•44•0•5•Updated Oct 1, 2024Oct 1, 2024

    • elk

      Public
      Keeping language models honest by directly eliciting knowledge encoded in their activations.
      Python
      •
      MIT License
      •33•182•14•10•Updated Sep 30, 2024Sep 30, 2024

    • website

      Public
      New website for EleutherAI based on Hugo static site generator
      HTML
      •6•4•0•2•Updated Sep 30, 2024Sep 30, 2024

    • aria-amt

      Public
      Efficient and robust implementation of seq-to-seq automatic piano transcription.
      Python
      •
      Apache License 2.0
      •7•19•0•0•Updated Sep 29, 2024Sep 29, 2024

    • cookbook

      Public
      Deep learning for dummies. All the practical details and useful utilities that go into working with real models.
      Python
      •
      Apache License 2.0
      •34•680•8•0•Updated Sep 24, 2024Sep 24, 2024

    • w2s

      Public
      Python
      •
      MIT License
      •0•15•1•0•Updated Sep 24, 2024Sep 24, 2024

    • ccs

      Public
      Python
      •
      MIT License
      •6•4•3•3•Updated Sep 24, 2024Sep 24, 2024

    • nanoGPT-mup

      Public
      The simplest, fastest repository for training/finetuning medium-sized GPTs.
      Python
      •
      MIT License
      •5.8k•65•0•0•Updated Sep 20, 2024Sep 20, 2024

    • monkfish

      Public
      Python
      •
      MIT License
      •1•4•0•0•Updated Sep 18, 2024Sep 18, 2024

    • features-across-time

      Public
      Understanding how features learned by neural networks evolve throughout training
      Python
      •
      MIT License
      •1•30•0•1•Updated Sep 16, 2024Sep 16, 2024

    • auto-circuit

      Public
      A library for efficient patching and automatic circuit discovery.
      Python
      •9•0•0•0•Updated Sep 16, 2024Sep 16, 2024

    • sae

      Public
      Sparse autoencoders
      Python
      •
      MIT License
      •40•312•3•1•Updated Sep 9, 2024Sep 9, 2024

    • pythia

      Public
      The hub for EleutherAI's work on interpretability and learning dynamics
      Jupyter Notebook
      •
      Apache License 2.0
      •163•2.2k•23•4•Updated Aug 21, 2024Aug 21, 2024

    • steering-llama3

      Public
      Python
      •0•2•0•0•Updated Aug 2, 2024Aug 2, 2024

    • huggingface.js

      Public
      Utilities to use the Hugging Face Hub API
      TypeScript
      •
      MIT License
      •213•1•0•0•Updated Jul 31, 2024Jul 31, 2024

    • aria

      Public
      Python
      •
      Apache License 2.0
      •11•39•0•0•Updated Jul 18, 2024Jul 18, 2024

    • llm-score-behavior

      Public
      Python
      •0•0•0•0•Updated Jul 3, 2024Jul 3, 2024

    • github-downloader

      Public
      Script for downloading GitHub.
      Python
      •41•87•0•5•Updated Jul 1, 2024Jul 1, 2024

    • CAA

      Public
      Steering Llama 2 with Contrastive Activation Addition
      Jupyter Notebook
      •
      MIT License
      •29•0•0•0•Updated Jun 30, 2024Jun 30, 2024

    • transformer-reasoning

      Public
      Experiments in transformer knowledge and reasoning
      Python
      •
      MIT License
      •12•0•0•0•Updated Jun 21, 2024Jun 21, 2024

    • rnngineering

      Public
      Engineering the state of RNN language models (Mamba, RWKV, etc.)
      Jupyter Notebook
      •
      MIT License
      •2•31•0•0•Updated May 25, 2024May 25, 2024