Token Classification
Transformers
Safetensors
leg-1.0-guardrail
feature-extraction
custom-code
safety
deberta-v2
sequence-classification
custom_code
Instructions to use clulab/LEG-1.0-aegis2.0-large with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use clulab/LEG-1.0-aegis2.0-large with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="clulab/LEG-1.0-aegis2.0-large", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("clulab/LEG-1.0-aegis2.0-large", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
Upload LEG model export
Browse files
README.md
CHANGED
|
@@ -86,7 +86,7 @@ If you are using this model, please cite:
|
|
| 86 |
@inproceedings{islam-etal-2026-leg,
|
| 87 |
title = "A Lightweight Explainable Guardrail for Prompt Safety",
|
| 88 |
author = "Islam, Md Asiful and Surdeanu, Mihai",
|
| 89 |
-
booktitle = "Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics
|
| 90 |
month = jul,
|
| 91 |
year = "2026",
|
| 92 |
address = "San Diego, USA",
|
|
|
|
| 86 |
@inproceedings{islam-etal-2026-leg,
|
| 87 |
title = "A Lightweight Explainable Guardrail for Prompt Safety",
|
| 88 |
author = "Islam, Md Asiful and Surdeanu, Mihai",
|
| 89 |
+
booktitle = "Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026)",
|
| 90 |
month = jul,
|
| 91 |
year = "2026",
|
| 92 |
address = "San Diego, USA",
|