Update README.md

README.md

@@ -21,8 +21,9 @@ input_ids = input_ids.cuda()
 outputs = model.generate(input_ids, do_sample=True, max_new_tokens=1024, top_p=0.85,
     temperature=0.3, repetition_penalty=1.2, eos_token_id=tokenizer.eos_token_id)
 
-output = tokenizer.decode(outputs[0])
-response = output.replace(text, "").replace('</s>', "")
+input_ids_len = input_ids.size(1)
+response_ids = outputs[0][input_ids_len:]
+response = tokenizer.decode(response_ids)
 print(response)
 ```