readme updated

README.md

@@ -7,9 +7,11 @@ tags:
 
 # text2tags-it
 
-The model has been trained on a collection of 11k articles with tags. Its purpose is to create tags suitable for the given article.
+The model has been trained on a collection of 11k news articles with tags. Its purpose is to create tags suitable for the given article.
 
-Sample code with a IlPost article:
+### Usage 
+
+Sample code with an article from IlPost:
 
 ```python
 from transformers import T5ForConditionalGeneration,T5Tokenizer
@@ -39,4 +41,13 @@ def tag(text: str):
 
 tags = tag(article)
 print(tags)
-```
+```
+
+### Overview
+
+- Model: T5 ([it5-small](https://huggingface.co/gsarti/it5-small))
+- Language: Italian
+- Downstream-task: Summarization (for topic tagging)
+- Training data: Custom dataset
+- Code: See example
+- Infrastructure: 1x T4