Text Classification
Transformers
Safetensors
deberta-v2
prompt-injection
injection-detection
safety
text-embeddings-inference
Instructions to use RyanStudio/Mezzo-Prompt-Guard-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use RyanStudio/Mezzo-Prompt-Guard-Base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="RyanStudio/Mezzo-Prompt-Guard-Base")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("RyanStudio/Mezzo-Prompt-Guard-Base") model = AutoModelForSequenceClassification.from_pretrained("RyanStudio/Mezzo-Prompt-Guard-Base", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Create .mezzoguard
Browse files- .mezzoguard +10 -0
.mezzoguard
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_type": "prompt_guard",
|
| 3 |
+
"mappings": {
|
| 4 |
+
"safe": "safe",
|
| 5 |
+
"unsafe": "unsafe"
|
| 6 |
+
},
|
| 7 |
+
"safe_category": "safe",
|
| 8 |
+
"default_max_seq_length": 64,
|
| 9 |
+
"default_overlap": 16
|
| 10 |
+
}
|