Instructions to use rwillh11/mdeberta_groups_2.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use rwillh11/mdeberta_groups_2.0 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="rwillh11/mdeberta_groups_2.0")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("rwillh11/mdeberta_groups_2.0") model = AutoModelForSequenceClassification.from_pretrained("rwillh11/mdeberta_groups_2.0", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -9,9 +9,8 @@ This model takes the various social groups that might be mentioned in political
|
|
| 9 |
|
| 10 |
See Dolinsky et al (2025) for more information on social group categories and Horne et al (2025) for details on training, relation to other models, and use cases.
|
| 11 |
|
| 12 |
-
📊 Evaluation Results: {'eval_loss': 0.
|
| 13 |
|
| 14 |
-
We found optimal hyper-parameters to be:
|
| 15 |
|
| 16 |
LEARNING_RATE = 1.9432557585419205e-05
|
| 17 |
WEIGHT_DECAY = 0.11740203810285466
|
|
|
|
| 9 |
|
| 10 |
See Dolinsky et al (2025) for more information on social group categories and Horne et al (2025) for details on training, relation to other models, and use cases.
|
| 11 |
|
| 12 |
+
📊 Evaluation Results: {'eval_loss': 0.023458, 'eval_accuracy': 0.994933, 'eval_f1': 0.894393, 'eval_precision': 0.0.897170, 'eval_recall': 0.891632, 'eval_runtime': 5.9184, 'eval_samples_per_second': 232.831, 'eval_steps_per_second': 29.231, 'epoch': 29.914368650217707}
|
| 13 |
|
|
|
|
| 14 |
|
| 15 |
LEARNING_RATE = 1.9432557585419205e-05
|
| 16 |
WEIGHT_DECAY = 0.11740203810285466
|