Text Classification
Transformers
Safetensors
Indonesian
English
multilingual
bert
mbert
utaut
technology-acceptance
indonesian
spam-detection
user-review-analysis
text-embeddings-inference
Instructions to use teguholix/BERTAUT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use teguholix/BERTAUT with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="teguholix/BERTAUT")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("teguholix/BERTAUT") model = AutoModelForSequenceClassification.from_pretrained("teguholix/BERTAUT", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Upload BERTAUT v1 report file classification_report.txt
Browse files
reports/v1/classification_report.txt
CHANGED
|
@@ -1,12 +1,12 @@
|
|
| 1 |
precision recall f1-score support
|
| 2 |
|
| 3 |
-
PE 0.
|
| 4 |
-
EE 0.
|
| 5 |
-
SI 0.
|
| 6 |
-
FC 0.
|
| 7 |
-
GR 0.
|
| 8 |
-
SP 0.
|
| 9 |
|
| 10 |
-
accuracy 0.91
|
| 11 |
-
macro avg 0.91 0.91 0.91
|
| 12 |
-
weighted avg 0.91 0.91 0.91
|
|
|
|
| 1 |
precision recall f1-score support
|
| 2 |
|
| 3 |
+
PE 0.90 0.94 0.92 1062
|
| 4 |
+
EE 0.91 0.92 0.92 1061
|
| 5 |
+
SI 0.88 0.92 0.90 1062
|
| 6 |
+
FC 0.89 0.94 0.92 1062
|
| 7 |
+
GR 0.96 0.92 0.94 1062
|
| 8 |
+
SP 0.94 0.84 0.89 1061
|
| 9 |
|
| 10 |
+
accuracy 0.91 6370
|
| 11 |
+
macro avg 0.91 0.91 0.91 6370
|
| 12 |
+
weighted avg 0.91 0.91 0.91 6370
|