Instructions to use s-nlp/Mutual_Implication_Score with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use s-nlp/Mutual_Implication_Score with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, RobertaForSequenceClassification_all_in_one_local tokenizer = AutoTokenizer.from_pretrained("s-nlp/Mutual_Implication_Score") model = RobertaForSequenceClassification_all_in_one_local.from_pretrained("s-nlp/Mutual_Implication_Score", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -15,7 +15,7 @@ Mutual Implication Score is a symmetric measure of text semantic similarity
|
|
| 15 |
based on a RoBERTA model pretrained for natural language inference
|
| 16 |
and fine-tuned on paraphrases dataset.
|
| 17 |
|
| 18 |
-
It is **particularly useful for paraphrases detection**, but can also be applied to other semantic similarity tasks, such as text style transfer.
|
| 19 |
|
| 20 |
## How to use
|
| 21 |
The following snippet illustrates code usage:
|
|
|
|
| 15 |
based on a RoBERTA model pretrained for natural language inference
|
| 16 |
and fine-tuned on paraphrases dataset.
|
| 17 |
|
| 18 |
+
It is **particularly useful for paraphrases detection**, but can also be applied to other semantic similarity tasks, such as content similarity scoring in text style transfer.
|
| 19 |
|
| 20 |
## How to use
|
| 21 |
The following snippet illustrates code usage:
|