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 ·
103fb43
1
Parent(s): 79effee
Update README.md
Browse files
README.md
CHANGED
|
@@ -2,7 +2,7 @@
|
|
| 2 |
license: apache-2.0
|
| 3 |
---
|
| 4 |
## Lutech-AI/I-SPIn
|
| 5 |
-
**I
|
| 6 |
This is a fine-tuned version of the model [paraphrase-multilingual-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-mpnet-base-v2).<br>
|
| 7 |
Its main task is to perform the [Natural Language Inference (NLI)](https://nlp.stanford.edu/projects/snli/) task in the Italian language.
|
| 8 |
|
|
@@ -11,12 +11,14 @@ Its main task is to perform the [Natural Language Inference (NLI)](https://nlp.s
|
|
| 11 |
2. Apply Knowledge Distillation on the output of (1.) with IT-EN translation dataset to retain NLI knowledge and improve Italian language comprehension.
|
| 12 |
|
| 13 |
## Usage #1 (HuggingFace Transformers)
|
| 14 |
-
Some additional code is needed in order for the model to work, since it provides the capability to
|
|
|
|
|
|
|
| 15 |
|
| 16 |
-
You need to include a folder, preferably called **ISPIn** in your project, structured like the folder **ISPIn** in this repo.
|
| 17 |
Files needed:
|
| 18 |
-
1. \_\_init\_\_.py (empty file)
|
| 19 |
-
2. ISPInConfig.py
|
| 20 |
3. ISPIn.py
|
| 21 |
|
| 22 |
Python code for ISPInConfig.py
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
---
|
| 4 |
## Lutech-AI/I-SPIn
|
| 5 |
+
**I**talian-**S**entence **P**air **In**ference, AKA **I-SPIn**.<br>
|
| 6 |
This is a fine-tuned version of the model [paraphrase-multilingual-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-mpnet-base-v2).<br>
|
| 7 |
Its main task is to perform the [Natural Language Inference (NLI)](https://nlp.stanford.edu/projects/snli/) task in the Italian language.
|
| 8 |
|
|
|
|
| 11 |
2. Apply Knowledge Distillation on the output of (1.) with IT-EN translation dataset to retain NLI knowledge and improve Italian language comprehension.
|
| 12 |
|
| 13 |
## Usage #1 (HuggingFace Transformers)
|
| 14 |
+
Some additional code is needed in order for the model to work, since it provides the capability to:
|
| 15 |
+
1. retrieve embeddings;
|
| 16 |
+
2. pass embeddings to a classifier to retrieve labels.
|
| 17 |
|
| 18 |
+
You need to include a folder, preferably called **ISPIn**, in your project, structured like the folder **ISPIn** in this repo.
|
| 19 |
Files needed:
|
| 20 |
+
1. \_\_init\_\_.py (empty file);
|
| 21 |
+
2. ISPInConfig.py;
|
| 22 |
3. ISPIn.py
|
| 23 |
|
| 24 |
Python code for ISPInConfig.py
|