Instructions to use cive202/humanize-ai-text-bart-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cive202/humanize-ai-text-bart-base with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="cive202/humanize-ai-text-bart-base")

# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("cive202/humanize-ai-text-bart-base")
model = AutoModelForSeq2SeqLM.from_pretrained("cive202/humanize-ai-text-bart-base", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use cive202/humanize-ai-text-bart-base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cive202/humanize-ai-text-bart-base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cive202/humanize-ai-text-bart-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/cive202/humanize-ai-text-bart-base

SGLang

How to use cive202/humanize-ai-text-bart-base with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "cive202/humanize-ai-text-bart-base" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cive202/humanize-ai-text-bart-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "cive202/humanize-ai-text-bart-base" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cive202/humanize-ai-text-bart-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use cive202/humanize-ai-text-bart-base with Docker Model Runner:
```
docker model run hf.co/cive202/humanize-ai-text-bart-base
```

cive202 commited on Apr 14

Commit

fd7ae4d

verified ·

1 Parent(s): 5fd97b0

Update README.md

Browse files

Files changed (1) hide show

README.md +24 -1

README.md CHANGED Viewed

@@ -131,4 +131,27 @@ Part of the unpublished 2026 manuscript:
 ## License
-MIT (placeholder). Ensure compatibility with `facebook/bart-base`.

 ## License
+MIT (placeholder). Ensure compatibility with `facebook/bart-base`.
+---
+## 📄 Paper
+This model is associated with the following research work:
+**“Rewriting the Machine: Encoder-Decoder vs. Decoder-Only Transformers for AI-to-Human Text Style Transfer”**
+- Authors: Utsav Paneru et al.
+- arXiv: https://arxiv.org/abs/2604.11687v1
+- Status: Preprint (2026)
+### Citation
+```bibtex
+@article{paneru2026rewriting,
+  title={Rewriting the Machine: Encoder-Decoder vs. Decoder-Only Transformers for AI-to-Human Text Style Transfer},
+  author={Paneru, Utsav and others},
+  journal={arXiv preprint arXiv:2604.11687},
+  year={2026}
+}