Update README.md

README.md

@@ -7,4 +7,23 @@ base_model:
 pipeline_tag: text2text-generation
 tags:
 - legal
----
+---
+
+## Usage
+```
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
+
+tokenizer = AutoTokenizer.from_pretrained("VerbACxSS/sempl-it-mt5-small")
+model = AutoModelForSeq2SeqLM.from_pretrained("VerbACxSS/sempl-it-mt5-small")
+
+model.eval()
+
+text_to_simplify = 'Nella fattispecie, questo documento è di natura prescrittiva'
+prompt = f'semplifica: {text_to_simplify}'
+
+x = tokenizer(prompt, max_length=1024, truncation=True, padding=True, return_tensors='pt').input_ids
+y = model.generate(x, max_length=1024)[0]
+output = tokenizer.decode(y, max_length=1024, truncation=True, skip_special_tokens=True, clean_up_tokenization_spaces=True)
+
+print(output)
+```