Update README.md

README.md

@@ -59,7 +59,7 @@ def generate(prompt, max_new_tokens=256):
     inputs = tokenizer(input, return_tensors='pt').to(device)
     output = model.generate(inputs['input_ids'],max_new_tokens=max_new_tokens, do_sample=False, temperature=1.0, eos_token_id=terminators)
     output = tokenizer.decode(output[0], skip_special_tokens=True) # set `skip_special_tokens=False` to debug
-    print(output)
+    return output
 ```
 
 test :