Instructions to use premsa/political-bias-prediction-allsides-DeBERTa with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use premsa/political-bias-prediction-allsides-DeBERTa with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="premsa/political-bias-prediction-allsides-DeBERTa")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("premsa/political-bias-prediction-allsides-DeBERTa") model = AutoModelForSequenceClassification.from_pretrained("premsa/political-bias-prediction-allsides-DeBERTa") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -24,8 +24,8 @@ training methodology:
|
|
| 24 |
- evaluate test split only on the model that performed best on validation loss
|
| 25 |
|
| 26 |
result summary:
|
| 27 |
-
- throughout the five training epochs, model of
|
| 28 |
-
- on test split
|
| 29 |
|
| 30 |
usage:
|
| 31 |
|
|
|
|
| 24 |
- evaluate test split only on the model that performed best on validation loss
|
| 25 |
|
| 26 |
result summary:
|
| 27 |
+
- throughout the five training epochs, model of fourth epoch achieved the lowest validation loss of 0.1909
|
| 28 |
+
- on test split fourth epoch model achieved f1 score of 0.9427 and a test loss of 0.2168
|
| 29 |
|
| 30 |
usage:
|
| 31 |
|