# EleutherAI/gpt-neo

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

Repository: https://github.com/EleutherAI/gpt-neo
Canonical: https://ross.abutalabs.com/products/gpt-neo
Homepage: https://www.eleuther.ai
Language: Python
License: MIT
License Family: permissive
Topics: language-model, transformers, gpt, gpt-2, gpt-3
Archived: true
Last push: 2022-02-25T06:27:12+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 2250, "days_push": 1650, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 8270, forks 954 (observed 2026-08-28T04:10:19.992801+00:00)

## What it is
GPT-Neo is EleutherAI's implementation of model- and data-parallel GPT-3-style transformer language models built on mesh-tensorflow, with released pretrained checkpoints (125M to 2.7B) trained on The Pile. The codebase is archived and no longer maintained, having been superseded by GPT-NeoX.

## Use cases
- train a GPT-3-style language model on TPUs
- run inference with pretrained open-source GPT models
- experiment with linear attention and mixture of experts in transformers
- study an open reproduction of GPT-3 architecture
- download open pretrained language model weights
- compare GPT-Neo against GPT-3 on benchmarks

## When to choose
- you need the original GPT-Neo checkpoints or mesh-tensorflow-based TPU training code
- you are reproducing historical research results on GPT-3-like models
- you want to study local attention, linear attention, or axial positional embeddings implementations

## When to avoid
- you want actively maintained LLM training code - use GPT-NeoX instead
- you just want to run pretrained GPT-Neo models - use the HuggingFace Transformers integration
- you need GPU-first or modern distributed training support

## Facets
- artifact type: library
- maturity: abandoned
- function: llm-training, llm-inference, transformers, machine-learning, deep-learning
- domain: large-language-models, deep-learning, machine-learning, artificial-intelligence
- platform: python, cloud
- tags: gpt-3, gpt-2, mesh-tensorflow, model-parallelism, tpu, language-model, archived, eleutherai, pretrained-models, the-pile, natural-language-processing, gpu, linux

## Member repositories
- EleutherAI/gpt-neo (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:19.992801+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:28:10.372457+00:00, confidence not recorded.
  - readme: https://github.com/EleutherAI/gpt-neo (fetched 2026-08-28T04:10:19.992801+00:00, sha a876d1099974)
  - homepage: https://www.eleuther.ai (fetched 2026-08-29T08:27:52.074303+00:00, sha 46c7f1a08777)
  - site_page: https://www.eleuther.ai/about (fetched 2026-08-29T08:27:52.088555+00:00, sha 8a099f02f9a1)
  - site_page: https://www.eleuther.ai/releases (fetched 2026-08-29T08:27:52.083712+00:00, sha 6b771c6c6df0)
- Data as of 2026-08-30T08:39:29.467469+00:00.