# kakaobrain/kogpt

KakaoBrain KoGPT (Korean Generative Pre-trained Transformer)

Repository: https://github.com/kakaobrain/kogpt
Canonical: https://ross.abutalabs.com/products/kogpt
Language: Python
License: NOASSERTION
License Family: other
Topics: deeplearning, gpt, nlp, transformers, huggingface, kogpt, kakaobrain, korean, generative-model, gpt3
Last push: 2024-01-30T10:54:08+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 1755, "days_push": 946, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1011, forks 135 (observed 2026-08-28T04:03:13.167685+00:00)

## What it is
KakaoBrain's KoGPT, a Korean Generative Pre-trained Transformer (GPT) model with 6B parameters, distributed via Hugging Face with inference tooling in Python. It provides pretrained weights (including float16 variants) for Korean language generation tasks.

## Use cases
- generate korean text with a pretrained gpt model
- run korean language model inference on gpu
- fine-tune a korean gpt for chatbot or generation tasks
- download kogpt weights from huggingface
- serve korean text completion via a cli

## When to choose
- you need a strong pretrained language model specifically for Korean
- you have a 16-32GB GPU and want open GPT-style Korean weights
- you want Hugging Face-compatible transformer checkpoints

## When to avoid
- you need a multilingual or English-focused model
- you have no GPU available
- you need permissively licensed weights for commercial use (weights are CC BY-NC-ND)

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, nlp, llm-inference, transformers
- domain: large-language-models, machine-learning
- platform: python
- tags: korean, gpt, huggingface, pretrained-model, text-generation, kakaobrain, natural-language-processing, gpu, linux

## Member repositories
- kakaobrain/kogpt (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:13.167685+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 2026-08-30T07:11:51.092367+00:00, confidence not recorded.
  - readme: https://github.com/kakaobrain/kogpt (fetched 2026-08-28T04:03:13.167685+00:00, sha cf4f8efa73f2)
- Data as of 2026-08-30T08:39:29.467469+00:00.