Text Classification
Transformers
Safetensors
Arabic
bert
arabic
arabert
social-media-analysis
threat-detection
streamlit
text-embeddings-inference
Instructions to use SoftALL/OBSIDIAN with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use SoftALL/OBSIDIAN with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="SoftALL/OBSIDIAN")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("SoftALL/OBSIDIAN") model = AutoModelForSequenceClassification.from_pretrained("SoftALL/OBSIDIAN") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -182,8 +182,9 @@ Classify CSV/XLSX files and display:
|
|
| 182 |
- uploaded file preview,
|
| 183 |
- selected text-column preview,
|
| 184 |
- classified result preview,
|
|
|
|
| 185 |
- label distribution chart,
|
| 186 |
-
- downloadable CSV output.
|
| 187 |
|
| 188 |
### Live Monitor Mode
|
| 189 |
|
|
@@ -195,10 +196,13 @@ Simulate or fetch near-real-time Arabic tweets and display:
|
|
| 195 |
- predicted label,
|
| 196 |
- confidence,
|
| 197 |
- alert level,
|
|
|
|
| 198 |
- high/medium alert table,
|
| 199 |
-
- label distribution chart,
|
|
|
|
|
|
|
| 200 |
- alert-level chart,
|
| 201 |
-
- downloadable CSV and Excel outputs.
|
| 202 |
|
| 203 |
The live-monitoring mode can optionally use an n8n webhook with the following parameters:
|
| 204 |
|
|
|
|
| 182 |
- uploaded file preview,
|
| 183 |
- selected text-column preview,
|
| 184 |
- classified result preview,
|
| 185 |
+
- label / keyword / minimum-confidence filters,
|
| 186 |
- label distribution chart,
|
| 187 |
+
- downloadable filtered CSV output.
|
| 188 |
|
| 189 |
### Live Monitor Mode
|
| 190 |
|
|
|
|
| 196 |
- predicted label,
|
| 197 |
- confidence,
|
| 198 |
- alert level,
|
| 199 |
+
- label / alert-level / keyword / minimum-confidence filters,
|
| 200 |
- high/medium alert table,
|
| 201 |
+
- label distribution pie chart,
|
| 202 |
+
- tweets-per-class bar chart,
|
| 203 |
+
- confidence distribution histogram,
|
| 204 |
- alert-level chart,
|
| 205 |
+
- downloadable filtered CSV and Excel outputs.
|
| 206 |
|
| 207 |
The live-monitoring mode can optionally use an n8n webhook with the following parameters:
|
| 208 |
|