Downloads · 30 days
26
28% of all-time downloads
roberta-hc3-detector
ahm1129/roberta-hc3-detector
roberta-hc3-detector is a text classification model from ahm1129. Use it when you need a label for a piece of text. The card lists the license as mit.
Fine-tuned roberta-base for binary classification of human-written vs AI-generated text.
All-time downloads
93
Public
Parameters
125M
499 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors499 MB · 99%
At a glance
- Task
- Text Classification
- License
- mit
- Model type
- roberta
- Access
- Public
- Created
- Jul 15, 2026
- Updated
- Jul 15, 2026
- SHA
- 35907fa7
Try a prompt
Model card
From the Hugging Face model README
RoBERTa-base — AI-Generated Text Detector (HC3)
Fine-tuned roberta-base for binary classification of human-written vs AI-generated text.
Trained as part of an MSc AI dissertation at the University of the West of Scotland (UWS), 2025/26. Supervisor: Dr Tahir Mahmood | Student: Abdul Hannaan Mohammed (B00409227)
Performance
| Condition | F1 | Accuracy | Recall |
|---|---|---|---|
| Clean HC3 (test) | 0.9913 | 0.9942 | 0.9995 |
| Pegasus paraphrase attack | — | — | ASR 1.2% |
| QuillBot-style attack | — | — | ASR 13.4% |
| ChatGPT rewrite attack | — | — | ASR 1.6% |
| M4 cross-dataset | 0.7389 | 0.7700 | — |
Training
- Base model: (Liu et al., 2019)
- Dataset: HC3 (Hello-SimpleAI/HC3) — 55,156 training samples, 70/15/15 split
- Epochs: 3 | LR: 2e-5 | Batch: 16 | Warmup: 500 steps
- Hardware: Local GPU (6 GB VRAM)
Usage
Citation
- Task
- Text Classification
- Type
- roberta
- License
- mit
- Languages
- en
- Created
- Jul 15, 2026
- Updated
- Jul 15, 2026