Instructions to use Lutech-AI/I-SPIn with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Lutech-AI/I-SPIn with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import ISPIn model = ISPIn.from_pretrained("Lutech-AI/I-SPIn", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit ·
0c2b60a
1
Parent(s): 0ff6910
Update README.md
Browse files
README.md
CHANGED
|
@@ -186,7 +186,17 @@ ISPIn(
|
|
| 186 |
```
|
| 187 |
|
| 188 |
## Evaluation results
|
| 189 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 190 |
|
| 191 |
## Next steps
|
| 192 |
1. Create an open library called ISPIn that lets the user to run directly the model without adding any additional code to a project.
|
|
|
|
| 186 |
```
|
| 187 |
|
| 188 |
## Evaluation results
|
| 189 |
+
```markdown
|
| 190 |
+
| Dataset | Metric | Performance |
|
| 191 |
+
|:--------------------------------------:|--------------|-------------|
|
| 192 |
+
| RTE3-ITA | Accuracy | 68% |
|
| 193 |
+
| RTE3-ITA | Min F1-Score | 60% |
|
| 194 |
+
| RTE-2009 | Accuracy | 59% |
|
| 195 |
+
| RTE-2009 | Min F1-Score | 31% |
|
| 196 |
+
| SNLI (IT) translated w/NLLB | Accuracy | 74% |
|
| 197 |
+
| MNLI-Matched (IT) translated w/NLLB | Accuracy | 72% |
|
| 198 |
+
| MNLI-Mismatched (IT) translated w/NLLB | Accuracy | 73% |
|
| 199 |
+
```
|
| 200 |
|
| 201 |
## Next steps
|
| 202 |
1. Create an open library called ISPIn that lets the user to run directly the model without adding any additional code to a project.
|