Instructions to use GenTelLab/gentelshield-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use GenTelLab/gentelshield-v1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="GenTelLab/gentelshield-v1")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("GenTelLab/gentelshield-v1") model = AutoModelForSequenceClassification.from_pretrained("GenTelLab/gentelshield-v1") - Notebooks
- Google Colab
- Kaggle
add metrics and dependencies
Browse files
README.md
CHANGED
|
@@ -1,3 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
|
| 2 |
# Model Details
|
| 3 |
|
|
@@ -96,4 +101,4 @@ We evaluate the model’s effectiveness in detecting Jailbreak, Goal Hijacking,
|
|
| 96 |
# Citation
|
| 97 |
```
|
| 98 |
Li, Rongchang, et al. "GenTel-Safe: A Unified Benchmark and Shielding Framework for Defending Against Prompt Injection Attacks" arXiv preprint arXiv:2409.19521 (2024).
|
| 99 |
-
```
|
|
|
|
| 1 |
+
---
|
| 2 |
+
metrics:
|
| 3 |
+
- accuracy
|
| 4 |
+
library_name: transformers
|
| 5 |
+
---
|
| 6 |
|
| 7 |
# Model Details
|
| 8 |
|
|
|
|
| 101 |
# Citation
|
| 102 |
```
|
| 103 |
Li, Rongchang, et al. "GenTel-Safe: A Unified Benchmark and Shielding Framework for Defending Against Prompt Injection Attacks" arXiv preprint arXiv:2409.19521 (2024).
|
| 104 |
+
```
|