# CodedotAl/gpt-code-clippy

Full description can be found here: https://discuss.huggingface.co/t/pretrain-gpt-neo-for-open-source-github-copilot-model/7678?u=ncoop57

Repository: https://github.com/CodedotAl/gpt-code-clippy
Canonical: https://ross.abutalabs.com/products/gpt-code-clippy
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2022-01-18T12:29:23+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 1889, "days_push": 1688, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3264, forks 217 (observed 2026-08-28T04:07:52.862216+00:00)

## What it is
GPT-Code-Clippy is an open-source effort to replicate GitHub Copilot by fine-tuning GPT-Neo language models on publicly available GitHub code. It includes dataset scraping, deduplication scripts, and trained model checkpoints released via Hugging Face.

## Use cases
- build an open source code completion model
- fine-tune GPT-Neo on GitHub code
- deduplicate large code datasets for training
- create a free alternative to GitHub Copilot
- train a language model for code autocompletion

## When to choose
- you want to train or study an open-source code completion model
- you need scripts for scraping and deduplicating GitHub code datasets
- you want to experiment with GPT-Neo for code generation

## When to avoid
- you need a production-ready code assistant with active maintenance
- you want a modern model architecture or up-to-date training data
- you need an editor plugin out of the box

## Facets
- artifact type: learning-resource
- maturity: abandoned
- function: machine-learning, llm-training, data-science, etl
- domain: large-language-models, machine-learning, developer-tools
- platform: python
- tags: code-generation, copilot-alternative, gpt-neo, huggingface, dataset-preparation, open-source-copilot

## Member repositories
- CodedotAl/gpt-code-clippy (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:52.862216+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 2026-08-30T07:23:11.166069+00:00, confidence not recorded.
  - readme: https://github.com/CodedotAl/gpt-code-clippy (fetched 2026-08-28T04:07:52.862216+00:00, sha 9e234d3526d9)
- Data as of 2026-08-30T08:39:29.467469+00:00.