Skip to content

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 8.8k 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 165 repositories
  • JavaScript 0 1 0 0 Updated May 1, 2025
  • sparsify Public

    Sparsify transformers with SAEs and transcoders

    Python 523 MIT 71 0 1 Updated May 1, 2025
  • cookbook Public

    Deep learning for dummies. All the practical details and useful utilities that go into working with real models.

    Python 787 Apache-2.0 40 8 0 Updated Apr 30, 2025
  • tyche Public

    Precisely estimating the volume of basins in neural net parameter space corresponding to interpretable behaviors

    Jupyter Notebook 7 Apache-2.0 0 0 0 Updated Apr 30, 2025
  • open-r1 Public Forked from huggingface/open-r1

    Fully open reproduction of DeepSeek-R1

    Python 2 Apache-2.0 2,227 0 0 Updated Apr 30, 2025
  • nanoGPT-mup Public Forked from karpathy/nanoGPT

    The simplest, fastest repository for training/finetuning medium-sized GPTs.

    Python 105 MIT 6,868 0 0 Updated Apr 29, 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 171 Apache-2.0 24 4 2 Updated Apr 29, 2025
  • lm-evaluation-harness Public

    A framework for few-shot evaluation of language models.

    Python 8,804 MIT 2,346 389 (18 issues need help) 122 Updated Apr 29, 2025
  • gpt-neox Public

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

    Python 7,169 Apache-2.0 1,053 64 (2 issues need help) 27 Updated Apr 28, 2025
  • elk Public

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

    Python 200 MIT 33 15 (1 issue needs help) 10 Updated Apr 28, 2025