Update README.md

README.md

@@ -57,4 +57,10 @@ print(model.config)
 
 tokenizer = AutoTokenizer.from_pretrained(MODEL_ID, trust_remote_code=True)
 
+text = "An attention function can be described as mapping a query and a set of key-value pairs to an output, where the query, keys, values, and output are all vectors. The output is"
+inputs = tokenizer(text, return_tensors="pt")
+outputs = model.generate(**inputs.to(model.device), max_new_tokens=100)
+result = tokenizer.decode(outputs[0], skip_special_tokens=True)
+print(result)
+
 ```