Metadata-Version: 2.4
Name: gohumanize-open-humanizer
Version: 0.1.1
Summary: Client and CLI for the GoHumanize Open Humanizer, an open Qwen3-4B fine-tune that rewrites AI-styled text into natural prose
Author: GoHumanize team
License-Expression: Apache-2.0
Project-URL: Homepage, https://gohumanize.ai/research
Project-URL: Repository, https://github.com/GoHumanize-ai/gohumanize-open-humanizer
Keywords: humanizer,ai-humanizer,humanize,humanize-text,humanize-ai-text,text-rewriting,rewriter,rewrite,paraphrase,paraphraser,style-transfer,writing-assistant,ai-writing,editing,prose,natural-language,open-model,open-source-model,qwen3,lora,fine-tune,llm,llm-tools,ai-tools,ai-assistant,gohumanize
Classifier: Programming Language :: Python :: 3
Classifier: Topic :: Text Processing :: Linguistic
Requires-Python: >=3.9
Description-Content-Type: text/markdown

# gohumanize-open-humanizer

[![PyPI](https://img.shields.io/pypi/v/gohumanize-open-humanizer)](https://pypi.org/project/gohumanize-open-humanizer/)
[![Model on Hugging Face](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-model-yellow)](https://huggingface.co/gohumanize/gohumanize-open-humanizer)
[![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.22843083.svg)](https://doi.org/10.5281/zenodo.22843083)
[![License: Apache 2.0](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://www.apache.org/licenses/LICENSE-2.0)

Python client and CLI for the **GoHumanize Open Humanizer**, an open Qwen3-4B
fine-tune (Apache-2.0) that rewrites AI-styled English text into more natural
human prose. Trained on 2,000 pairs built from public-domain books.

```bash
pip install gohumanize-open-humanizer
open-humanizer "It is worth noting that the committee reached a consensus."
```

```python
from gohumanize_open_humanizer import Humanizer

# Your own copy of the model, which needs no key:
#   ollama pull hf.co/gohumanize/gohumanize-open-humanizer:Q4_K_M
h = Humanizer(base_url="http://localhost:11434/v1",
              model="hf.co/gohumanize/gohumanize-open-humanizer:Q4_K_M")
print(h.humanize("It is worth noting that the committee reached a consensus."))

# Humanizer() with no arguments points at the endpoint behind the browser demo,
# which is rate-limited and needs OPEN_HUMANIZER_API_KEY. To try the model without
# installing anything, use the demo at https://gohumanize.ai/research
```

Environment variables `OPEN_HUMANIZER_URL`, `OPEN_HUMANIZER_MODEL` and
`OPEN_HUMANIZER_API_KEY` set the same options. No dependencies beyond the
standard library.

The model is an educational release: it is separate from the production models
of GoHumanize.ai and makes no claim about AI detectors.

## Links

| Resource | Link |
| --- | --- |
| Project page and browser demo | [gohumanize.ai/research](https://gohumanize.ai/research) |
| Model weights, LoRA adapter, GGUF builds | [gohumanize/gohumanize-open-humanizer](https://huggingface.co/gohumanize/gohumanize-open-humanizer) |
| Dataset, 2,200 pairs (CC-BY 4.0) | [gohumanize/gohumanize-open-humanizer-dataset](https://huggingface.co/datasets/gohumanize/gohumanize-open-humanizer-dataset) |
| Code and full pipeline | [GoHumanize-ai/gohumanize-open-humanizer](https://github.com/GoHumanize-ai/gohumanize-open-humanizer) |
| Write-up: every step, service and result | [docs/paper.md](https://github.com/GoHumanize-ai/gohumanize-open-humanizer/blob/main/docs/paper.md) |
| Archived release, citable DOI | [10.5281/zenodo.22843083](https://doi.org/10.5281/zenodo.22843083) |
| Python client and CLI | [pypi.org/project/gohumanize-open-humanizer](https://pypi.org/project/gohumanize-open-humanizer/) |
| MCP server for AI assistants | [npm](https://www.npmjs.com/package/gohumanize-open-humanizer-mcp) · [source](https://github.com/GoHumanize-ai/gohumanize-open-humanizer-mcp) |
| Training run, loss curves and config | [Weights & Biases](https://wandb.ai/gohumanize/gohumanize-open-humanizer/runs/95wi8tdg) |
