Text Classification
Transformers
Safetensors
Hebrew
bert
profanity-detection
toxicity
hebrew
alephbert
text-embeddings-inference
Instructions to use LikoKIko/OpenCensor-H1-Mini with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use LikoKIko/OpenCensor-H1-Mini with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="LikoKIko/OpenCensor-H1-Mini")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("LikoKIko/OpenCensor-H1-Mini") model = AutoModelForSequenceClassification.from_pretrained("LikoKIko/OpenCensor-H1-Mini") - Notebooks
- Google Colab
- Kaggle
LikoKiko commited on
Commit ·
0e7f17a
1
Parent(s): 3a8d54b
Init
Browse files
README.md
CHANGED
|
@@ -42,7 +42,7 @@ metrics:
|
|
| 42 |
| **Precision** | 0.9812 |
|
| 43 |
| **Recall** | 0.9835 |
|
| 44 |
|
| 45 |
-
*Note: Best Threshold = 0.
|
| 46 |
|
| 47 |
### Training Graphs
|
| 48 |
|
|
@@ -83,7 +83,7 @@ def predict(text):
|
|
| 83 |
return {
|
| 84 |
"text": text,
|
| 85 |
"score": round(score, 4),
|
| 86 |
-
"is_toxic": score >= 0.
|
| 87 |
}
|
| 88 |
|
| 89 |
# Example usage
|
|
|
|
| 42 |
| **Precision** | 0.9812 |
|
| 43 |
| **Recall** | 0.9835 |
|
| 44 |
|
| 45 |
+
*Note: Best Threshold = 0.17*
|
| 46 |
|
| 47 |
### Training Graphs
|
| 48 |
|
|
|
|
| 83 |
return {
|
| 84 |
"text": text,
|
| 85 |
"score": round(score, 4),
|
| 86 |
+
"is_toxic": score >= 0.17 # Threshold
|
| 87 |
}
|
| 88 |
|
| 89 |
# Example usage
|