Skip to content
@EleutherAI

EleutherAI

Pinned Loading

  1. gpt-neox Public

    An implementation of model parallel autoregressive transformers on GPUs, based on the Megatron and DeepSpeed libraries

    Python 7.2k 1.1k

  2. lm-evaluation-harness Public

    A framework for few-shot evaluation of language models.

    Python 8.7k 2.3k

  3. minetest Public

    Forked from luanti-org/luanti

    Minetest is an open source voxel game engine with easy modding and game creation

    C++ 65 11

  4. pythia Public

    The hub for EleutherAI's work on interpretability and learning dynamics

    Jupyter Notebook 2.5k 183

Repositories

Showing 10 of 164 repositories
  • open-r1 Public Forked from huggingface/open-r1

    Fully open reproduction of DeepSeek-R1

    Python 1 Apache-2.0 2,217 0 0 Updated Apr 24, 2025
  • fmri Public

    Analogue of fMRI on artificial neural networks

    0 MIT 0 0 0 Updated Apr 24, 2025
  • truffaldino Public

    Investigating goal instability in RL

    Python 0 MIT 0 0 0 Updated Apr 24, 2025
  • POSER Public Forked from sevdeawesome/POSER

    Poser: Unmasking Alignment Faking LLMs by Manipulating Their Internals

    Python 1 1 0 0 Updated Apr 24, 2025
  • gpt-neox Public

    An implementation of model parallel autoregressive transformers on GPUs, based on the Megatron and DeepSpeed libraries

    Python 7,164 Apache-2.0 1,051 64 (2 issues need help) 26 Updated Apr 23, 2025
  • delphi Public

    Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models know themselves through automated interpretability.

    Python 169 Apache-2.0 25 4 2 Updated Apr 23, 2025
  • sparsify Public

    Sparsify transformers with SAEs and transcoders

    Python 521 MIT 70 0 0 Updated Apr 22, 2025
  • elk Public

    Keeping language models honest by directly eliciting knowledge encoded in their activations.

    Python 199 MIT 33 15 (1 issue needs help) 10 Updated Apr 21, 2025
  • lm-evaluation-harness Public

    A framework for few-shot evaluation of language models.

    Python 8,735 MIT 2,323 380 (18 issues need help) 116 Updated Apr 18, 2025
  • rllm Public Forked from agentica-project/rllm

    Democratizing Reinforcement Learning for LLMs

    Jupyter Notebook 0 MIT 287 0 0 Updated Apr 16, 2025
View all repositories