denocris commited on
Commit
c7bac13
1 Parent(s): d8aeadf

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +31 -0
README.md ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: it
3
+ license: mit
4
+ ---
5
+
6
+ # WineBERTo 🍷🥂
7
+
8
+ **wineberto-italian-cased** is a BERT model obtained by MLM adaptive-tuning [**bert-base-italian-xxl-cased**](https://huggingface.co/dbmdz/bert-base-italian-xxl-cased) model on Italian drink recipes and wine descriptions, approximately 77k sentences (3.3M words).
9
+
10
+ **Author:** Cristiano De Nobili ([@denocris](https://twitter.com/denocris) on Twitter, [LinkedIn](https://www.linkedin.com/in/cristiano-de-nobili/)) for [VINHOOD](https://www.vinhood.com/en/).
11
+ <p>
12
+ <img src="https://drive.google.com/uc?export=view&id=1dco9I9uzevP2V6oku1salIYcovUAeqWE" width="400"> </br>
13
+ </p>
14
+
15
+ # Perplexity
16
+
17
+ Test set of 14k sentences about food.
18
+
19
+ | Model | Perplexity |
20
+ | ------ | ------ |
21
+ | wineberto-italian-cased | **2.29** |
22
+ | bert-base-italian-xxl-cased | 4.60 |
23
+
24
+ # Usage
25
+
26
+ ```python
27
+ from transformers import AutoModel, AutoTokenizer
28
+ model_name = "winehood/chefberto-italian-cased"
29
+ tokenizer = AutoTokenizer.from_pretrained(model_name)
30
+ model = AutoModel.from_pretrained(model_name)
31
+ ```