Transformers
PyTorch
I-SPIn
Lutech-admin commited on
Commit
64ee658
·
1 Parent(s): ee827d5

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -2
README.md CHANGED
@@ -5,8 +5,10 @@ license: apache-2.0
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.<br>
8
- The prediction label has two possible values: 1 means the model predicts <em>entailment</em>, 0 represents the <em>neutral</em> case
9
- while -1 corresponds to <em>contradiction</em>.
 
 
10
 
11
  ## How it was trained
12
  1. Train [paraphrase-multilingual-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-mpnet-base-v2) on the NLI task;
 
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.<br>
8
+ The prediction labels may assume three possible values:
9
+ 1. 1 means the model predicts <em>entailment</em>;
10
+ 2. 0 represents the <em>neutral</em> case;
11
+ 3. -1 corresponds to <em>contradiction</em>.
12
 
13
  ## How it was trained
14
  1. Train [paraphrase-multilingual-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-mpnet-base-v2) on the NLI task;