# Turing-Project/WriteGPT

由图灵的猫开发，基于开源GPT2.0的初代创作型人工智能 | 可扩展、可进化

Repository: https://github.com/Turing-Project/WriteGPT
Canonical: https://ross.abutalabs.com/products/writegpt
Language: Python
License: MIT
License Family: permissive
Last push: 2024-03-31T05:56:54+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": 2164, "days_push": 885, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 5289, forks 881 (observed 2026-08-28T04:09:15.113773+00:00)

## What it is
WriteGPT is a generative text-creation AI framework built on GPT-2 and other models (EAST, CRNN, BERT), fine-tuned to generate Chinese exam-style argumentative essays. It provides an end-to-end pipeline from exam paper OCR recognition to essay output, with a Colab demo.

## Use cases
- generate Chinese argumentative essays automatically
- fine-tune GPT-2 on Chinese text corpora
- run OCR on exam papers and output essays
- demo text generation in Colab

## When to choose
- you want to experiment with Chinese GPT-2 text generation
- you need an end-to-end OCR-to-text-generation pipeline
- you want a research/educational example of fine-tuned generative models

## When to avoid
- you need production-grade modern LLM inference
- you require up-to-date maintained dependencies (TensorFlow 1.x)
- you need English or multilingual essay generation

## Facets
- artifact type: framework
- maturity: maintenance
- function: machine-learning, nlp, ocr, deep-learning
- domain: artificial-intelligence, machine-learning
- platform: python
- tags: gpt-2, text-generation, essay-writing, chinese, tensorflow, fine-tuning, natural-language-processing, linux, gpu

## Member repositories
- Turing-Project/WriteGPT (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:15.113773+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 2026-08-29T17:59:13.041087+00:00, confidence not recorded.
  - readme: https://github.com/Turing-Project/WriteGPT (fetched 2026-08-28T04:09:15.113773+00:00, sha 950ea1bb70f8)
- Data as of 2026-08-30T08:39:29.467469+00:00.