Skip to content

Pinned Loading

  1. gpt-neox gpt-neox Public

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

    Python 7.1k 1k

  2. lm-evaluation-harness lm-evaluation-harness Public

    A framework for few-shot evaluation of language models.

    Python 7.6k 2k

  3. minetest minetest Public

    Forked from luanti-org/luanti

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

    C++ 64 10

  4. pythia pythia Public

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

    Jupyter Notebook 2.4k 175

Repositories

Showing 10 of 156 repositories
  • polyapprox Public

    Closed-form polynomial approximations to neural networks

    EleutherAI/polyapprox’s past year of commit activity
    Python 2 MIT 0 0 0 Updated Jan 30, 2025
  • basin-volume Public

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

    EleutherAI/basin-volume’s past year of commit activity
    Jupyter Notebook 1 Apache-2.0 0 0 0 Updated Jan 30, 2025
  • lm-evaluation-harness Public

    A framework for few-shot evaluation of language models.

    EleutherAI/lm-evaluation-harness’s past year of commit activity
    Python 7,596 MIT 2,044 350 (21 issues need help) 97 Updated Jan 30, 2025
  • transformer-reasoning Public Forked from OSU-NLP-Group/GrokkedTransformer

    Experiments in transformer knowledge and reasoning

    EleutherAI/transformer-reasoning’s past year of commit activity
    Jupyter Notebook 10 MIT 13 0 0 Updated Jan 30, 2025
  • gpt-neox Public

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

    EleutherAI/gpt-neox’s past year of commit activity
    Python 7,063 Apache-2.0 1,039 62 (3 issues need help) 23 Updated Jan 29, 2025
  • DeeperSpeed Public Forked from microsoft/DeepSpeed

    DeepSpeed is a deep learning optimization library that makes distributed training easy, efficient, and effective.

    EleutherAI/DeeperSpeed’s past year of commit activity
    Python 164 Apache-2.0 4,382 0 2 Updated Jan 29, 2025
  • TransformerEngine Public Forked from NVIDIA/TransformerEngine

    A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper and Ada GPUs, to provide better performance with lower memory utilization in both training and inference.

    EleutherAI/TransformerEngine’s past year of commit activity
    Python 0 Apache-2.0 355 0 0 Updated Jan 29, 2025
  • sae_overlap Public

    Acompanying code for our research on SAE feature overlap when trained on different seeds.

    EleutherAI/sae_overlap’s past year of commit activity
    Jupyter Notebook 1 Apache-2.0 1 0 0 Updated Jan 28, 2025
  • mdl Public

    Minimum Description Length probing for neural network representations

    EleutherAI/mdl’s past year of commit activity
    Python 18 MIT 2 0 2 Updated Jan 28, 2025
  • elk Public

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

    EleutherAI/elk’s past year of commit activity
    Python 193 MIT 33 15 (1 issue needs help) 10 Updated Jan 27, 2025