EleutherAI

Repositories

• gpt-neox

  An implementation of model parallel GPT-3-like models on GPUs, based on the DeepSpeed library. Designed to be able to train models in the hundreds of billions of parameters or larger.

  transformers language-model gpt-3 deepspeed-library
  Python Apache-2.0 88 965 13 (1 issue needs help) 1 Updated Jul 6, 2021

• text-generation-testing-ui

  Web app for demoing the EAI models
  JavaScript MIT 0 0 5 0 Updated Jul 5, 2021

• DeeperSpeed

  Forked from microsoft/DeepSpeed

  DeepSpeed is a deep learning optimization library that makes distributed training easy, efficient, and effective.
  Python MIT 528 20 0 1 Updated Jul 3, 2021

• lm-evaluation-harness

  A framework for few-shot evaluation of autoregressive language models.
  Python MIT 35 84 48 (9 issues need help) 3 Updated Jul 3, 2021

• attention-ensemble
  0 0 0 0 Updated Jul 3, 2021

• new-website

  New website for EleutherAI based on Hugo static site generator
  HTML 2 4 0 1 Updated Jul 2, 2021

• mp_nerf

  Massively-Parallel Natural Extension of Reference Frame
  Jupyter Notebook 1 6 0 0 Updated Jun 30, 2021

• CARP
  Python 0 7 0 0 Updated Jun 29, 2021

• project-menu

  See the issue board for the current status of active and prospective projects!
  1 4 10 (2 issues need help) 0 Updated Jun 28, 2021

• gpt-neo

  An implementation of model parallel GPT-2 and GPT-3-style models using the mesh-tensorflow library.

  transformers gpt language-model gpt-2 gpt-3
  Python MIT 388 5,246 10 9 Updated Jun 26, 2021

• isaac-mchorse

  EleutherAI's discord bot
  Python 0 2 0 0 Updated Jun 26, 2021

• pyfra

  Python Research Framework
  Python MIT 2 62 6 0 Updated Jun 23, 2021

• best-download

  URL downloader supporting checkpointing and continuous checksumming.
  Python MIT 2 6 0 0 Updated Jun 18, 2021

• the-pile
  Python MIT 36 456 1 0 Updated Jun 16, 2021

• openwebtext2
  Python MIT 3 28 0 0 Updated Jun 11, 2021

• BIG-bench

  Forked from google/BIG-bench

  Beyond the Imitation Game collaborative benchmark for enormous language models
  Jupyter Notebook Apache-2.0 237 0 0 0 Updated May 31, 2021

• equivariance

  A framework for implementing equivariant DL
  Jupyter Notebook Apache-2.0 3 11 0 0 Updated May 25, 2021

• visual-grounding

  Visually ground GPT-Neo 1.3b and 2.7b
  Python Apache-2.0 5 5 0 0 Updated May 7, 2021

• visual-grounding-jax

  Experiments pertaining to visually grounding Neo, built off of mesh-transformer-jax
  GPL-3.0 0 0 0 0 Updated May 4, 2021

• distilling

  Experiments with distilling large language models.
  Python MIT 2 13 0 0 Updated May 3, 2021

• kube

  Kubernetes deployment library
  Python 0 2 0 0 Updated May 3, 2021

• pile-enron-emails

  A script for collecting the Enron Emails dataset in a language modelling friendly format.
  Python CC0-1.0 4 2 0 1 Updated Apr 25, 2021

• poll_website_demo

  Flask Based Polling Website Demo
  Python MIT 0 0 0 0 Updated Apr 17, 2021

• pile-website

  Forked from rajpurkar/SQuAD-explorer
  HTML 101 1 0 0 Updated Apr 13, 2021

• DALLE-mtf

  Open-AI's DALL-E for large scale training in mesh-tensorflow.

  transformers artificial-intelligence autoregressive text-to-image variational-autoencoder multimodal
  Python MIT 33 343 2 3 Updated Apr 6, 2021

• transformers

  Forked from huggingface/transformers

  🤗Transformers: State-of-the-art Natural Language Processing for Pytorch and TensorFlow 2.0.
  Python Apache-2.0 11,352 0 0 0 Updated Apr 4, 2021

• github-downloader

  Forked from noanabeshima/github-downloader

  Script for downloading GitHub.
  Python 9 8 0 2 Updated Apr 1, 2021

• info Archived

  (Deprecated) A hub for onboarding & other information.
  3 77 0 0 Updated Mar 31, 2021

• scaling-laws
  Jupyter Notebook Apache-2.0 0 0 0 0 Updated Mar 11, 2021

• lm_perplexity
  Python MIT 5 26 0 0 Updated Mar 6, 2021