Text Generation
Transformers
Safetensors
English
bart
text2text-generation
style-transfer
rewriting
humanization
seq2seq
evaluation
bertscore
rouge
chrf
Instructions to use cive202/humanize-ai-text-bart-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
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
Update README.md
Browse files
README.md
CHANGED
|
@@ -16,6 +16,8 @@ tags:
|
|
| 16 |
library_name: transformers
|
| 17 |
base_model: facebook/bart-base
|
| 18 |
pipeline_tag: text-generation
|
|
|
|
|
|
|
| 19 |
---
|
| 20 |
|
| 21 |
# cive202/humanize-ai-text-bart-base
|
|
@@ -28,6 +30,24 @@ Fine-tuned **BART-base** (`facebook/bart-base`) for **AI → Human rewriting** (
|
|
| 28 |
|
| 29 |
---
|
| 30 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 31 |
## Quickstart
|
| 32 |
|
| 33 |
```bash
|
|
@@ -135,23 +155,5 @@ MIT (placeholder). Ensure compatibility with `facebook/bart-base`.
|
|
| 135 |
|
| 136 |
---
|
| 137 |
|
| 138 |
-
## 📄 Paper
|
| 139 |
-
|
| 140 |
-
This model is associated with the following research work:
|
| 141 |
-
|
| 142 |
-
**“Rewriting the Machine: Encoder-Decoder vs. Decoder-Only Transformers for AI-to-Human Text Style Transfer”**
|
| 143 |
-
|
| 144 |
-
- Authors: Utsav Paneru et al.
|
| 145 |
-
- arXiv: https://arxiv.org/abs/2604.11687v1
|
| 146 |
-
- Status: Preprint (2026)
|
| 147 |
-
|
| 148 |
-
### Citation
|
| 149 |
|
| 150 |
-
```bibtex
|
| 151 |
-
@article{paneru2026rewriting,
|
| 152 |
-
title={Rewriting the Machine: Encoder-Decoder vs. Decoder-Only Transformers for AI-to-Human Text Style Transfer},
|
| 153 |
-
author={Paneru, Utsav and others},
|
| 154 |
-
journal={arXiv preprint arXiv:2604.11687},
|
| 155 |
-
year={2026}
|
| 156 |
-
}
|
| 157 |
|
|
|
|
| 16 |
library_name: transformers
|
| 17 |
base_model: facebook/bart-base
|
| 18 |
pipeline_tag: text-generation
|
| 19 |
+
paper:
|
| 20 |
+
- https://arxiv.org/abs/2604.11687v1
|
| 21 |
---
|
| 22 |
|
| 23 |
# cive202/humanize-ai-text-bart-base
|
|
|
|
| 30 |
|
| 31 |
---
|
| 32 |
|
| 33 |
+
## 📄 Paper
|
| 34 |
+
|
| 35 |
+
**“Rewriting the Machine: Encoder-Decoder vs. Decoder-Only Transformers for AI-to-Human Text Style Transfer”**
|
| 36 |
+
**Authors:** Utsav Paneru et al.
|
| 37 |
+
**arXiv:** https://arxiv.org/abs/2604.11687v1
|
| 38 |
+
**Status:** Preprint (2026)
|
| 39 |
+
|
| 40 |
+
### Citation
|
| 41 |
+
|
| 42 |
+
```bibtex
|
| 43 |
+
@article{paneru2026rewriting,
|
| 44 |
+
title={Rewriting the Machine: Encoder-Decoder vs. Decoder-Only Transformers for AI-to-Human Text Style Transfer},
|
| 45 |
+
author={Paneru, Utsav and others},
|
| 46 |
+
journal={arXiv preprint arXiv:2604.11687},
|
| 47 |
+
year={2026}
|
| 48 |
+
}
|
| 49 |
+
```
|
| 50 |
+
|
| 51 |
## Quickstart
|
| 52 |
|
| 53 |
```bash
|
|
|
|
| 155 |
|
| 156 |
---
|
| 157 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 158 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 159 |
|