Text Classification
Transformers
ONNX
Safetensors
llama
safety
content-moderation
multi-label
multilingual
tiny-language-model
from-scratch
distilled
text-embeddings-inference
Instructions to use KucLab/Barist.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use KucLab/Barist.1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="KucLab/Barist.1")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("KucLab/Barist.1") model = AutoModelForSequenceClassification.from_pretrained("KucLab/Barist.1", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Add report adversarial.json
Browse files- reports/adversarial.json +12 -12
reports/adversarial.json
CHANGED
|
@@ -1,36 +1,36 @@
|
|
| 1 |
{
|
| 2 |
-
"checkpoint": "
|
| 3 |
"n_items": 160,
|
| 4 |
"attacks": {
|
| 5 |
"clean": {
|
| 6 |
"n": 160,
|
| 7 |
"detection_rate@0.5": 0.9875,
|
| 8 |
-
"mean_unsafe_prob": 0.
|
| 9 |
},
|
| 10 |
"typo": {
|
| 11 |
"n": 160,
|
| 12 |
-
"detection_rate@0.5": 0.
|
| 13 |
-
"mean_unsafe_prob": 0.
|
| 14 |
},
|
| 15 |
"leet": {
|
| 16 |
"n": 160,
|
| 17 |
-
"detection_rate@0.5": 0.
|
| 18 |
-
"mean_unsafe_prob": 0.
|
| 19 |
},
|
| 20 |
"homoglyph": {
|
| 21 |
"n": 160,
|
| 22 |
-
"detection_rate@0.5":
|
| 23 |
-
"mean_unsafe_prob": 0.
|
| 24 |
},
|
| 25 |
"zero_width": {
|
| 26 |
"n": 160,
|
| 27 |
-
"detection_rate@0.5":
|
| 28 |
-
"mean_unsafe_prob": 0.
|
| 29 |
},
|
| 30 |
"case": {
|
| 31 |
"n": 160,
|
| 32 |
-
"detection_rate@0.5": 0.
|
| 33 |
-
"mean_unsafe_prob": 0.
|
| 34 |
}
|
| 35 |
}
|
| 36 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"checkpoint": "checkpoints_b1q/best.pt",
|
| 3 |
"n_items": 160,
|
| 4 |
"attacks": {
|
| 5 |
"clean": {
|
| 6 |
"n": 160,
|
| 7 |
"detection_rate@0.5": 0.9875,
|
| 8 |
+
"mean_unsafe_prob": 0.8576
|
| 9 |
},
|
| 10 |
"typo": {
|
| 11 |
"n": 160,
|
| 12 |
+
"detection_rate@0.5": 0.9437,
|
| 13 |
+
"mean_unsafe_prob": 0.8012
|
| 14 |
},
|
| 15 |
"leet": {
|
| 16 |
"n": 160,
|
| 17 |
+
"detection_rate@0.5": 0.9875,
|
| 18 |
+
"mean_unsafe_prob": 0.8527
|
| 19 |
},
|
| 20 |
"homoglyph": {
|
| 21 |
"n": 160,
|
| 22 |
+
"detection_rate@0.5": 0.9938,
|
| 23 |
+
"mean_unsafe_prob": 0.8942
|
| 24 |
},
|
| 25 |
"zero_width": {
|
| 26 |
"n": 160,
|
| 27 |
+
"detection_rate@0.5": 1.0,
|
| 28 |
+
"mean_unsafe_prob": 0.8925
|
| 29 |
},
|
| 30 |
"case": {
|
| 31 |
"n": 160,
|
| 32 |
+
"detection_rate@0.5": 0.9625,
|
| 33 |
+
"mean_unsafe_prob": 0.7973
|
| 34 |
}
|
| 35 |
}
|
| 36 |
}
|