Instructions to use TurkuNLP/web-register-classification-en with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use TurkuNLP/web-register-classification-en with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="TurkuNLP/web-register-classification-en")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("TurkuNLP/web-register-classification-en") model = AutoModelForSequenceClassification.from_pretrained("TurkuNLP/web-register-classification-en", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -209,8 +209,8 @@ The model was trained using the Multilingual CORE Corpora, which will be publish
|
|
| 209 |
#### Training Hyperparameters
|
| 210 |
|
| 211 |
- **Batch size:** 8
|
| 212 |
-
- **Epochs:**
|
| 213 |
-
- **Learning rate:** 0.
|
| 214 |
- **Precision:** bfloat16 (non-mixed precision)
|
| 215 |
- **TF32:** Enabled
|
| 216 |
- **Seed:** 42
|
|
|
|
| 209 |
#### Training Hyperparameters
|
| 210 |
|
| 211 |
- **Batch size:** 8
|
| 212 |
+
- **Epochs:** 9
|
| 213 |
+
- **Learning rate:** 0.00003
|
| 214 |
- **Precision:** bfloat16 (non-mixed precision)
|
| 215 |
- **TF32:** Enabled
|
| 216 |
- **Seed:** 42
|