Commit ·
524b730
1
Parent(s): bab2511
Update README.md
Browse files
README.md
CHANGED
|
@@ -14,7 +14,7 @@ The prediction labels may assume three possible values:
|
|
| 14 |
1. Train [paraphrase-multilingual-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-mpnet-base-v2) on the NLI task;
|
| 15 |
2. Apply Knowledge Distillation on the output of (1.) with IT-EN translation dataset to retain NLI knowledge and improve Italian language comprehension.
|
| 16 |
|
| 17 |
-
## Usage #1 (HuggingFace Transformers)
|
| 18 |
In the environment on which you want to run the project, type:
|
| 19 |
```markdown
|
| 20 |
pip install --extra-index-url https://test.pypi.org/simple/ ispin
|
|
@@ -53,7 +53,7 @@ predictions = model.predict(
|
|
| 53 |
print(predictions) # -> [0 -1]
|
| 54 |
```
|
| 55 |
|
| 56 |
-
## Usage #2 (cloning repo) (will be deleted)
|
| 57 |
In a terminal located in your project folder, type: 'git clone https://huggingface.co/Lutech-AI/I-SPIn/ ISPIn'. <br>
|
| 58 |
Please specify the final 'ISPIn' to avoid complications when calling the Python module. <br>
|
| 59 |
Then, in the code where you call the model, substitute the line:
|
|
|
|
| 14 |
1. Train [paraphrase-multilingual-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-mpnet-base-v2) on the NLI task;
|
| 15 |
2. Apply Knowledge Distillation on the output of (1.) with IT-EN translation dataset to retain NLI knowledge and improve Italian language comprehension.
|
| 16 |
|
| 17 |
+
### Usage #1 (HuggingFace Transformers)
|
| 18 |
In the environment on which you want to run the project, type:
|
| 19 |
```markdown
|
| 20 |
pip install --extra-index-url https://test.pypi.org/simple/ ispin
|
|
|
|
| 53 |
print(predictions) # -> [0 -1]
|
| 54 |
```
|
| 55 |
|
| 56 |
+
### Usage #2 (cloning repo) (will be deleted)
|
| 57 |
In a terminal located in your project folder, type: 'git clone https://huggingface.co/Lutech-AI/I-SPIn/ ISPIn'. <br>
|
| 58 |
Please specify the final 'ISPIn' to avoid complications when calling the Python module. <br>
|
| 59 |
Then, in the code where you call the model, substitute the line:
|