Instructions to use igorktech/rubert-tiny-review with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use igorktech/rubert-tiny-review with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="igorktech/rubert-tiny-review")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("igorktech/rubert-tiny-review") model = AutoModelForSequenceClassification.from_pretrained("igorktech/rubert-tiny-review") - Notebooks
- Google Colab
- Kaggle
metadata
widget:
- text: Мне не понравился ваш товар
example_title: Example
Model card
Trained on open joined datasets:
- clothes reviews
- different shops reviews
Data distribution
| FIELD1 | sentiment |
|---|---|
| positive | 114599 |
| neutral | 29079 |
| negative | 28772 |
Score
| FIELD1 | binary | micro | macro |
|---|---|---|---|
| 0 | 0.7165 | 0.9137 | 0.8328 |
| 1 | 0.6011 | 0.8782 | 0.7646 |
| 2 | 0.9542 | 0.94 | 0.9336 |