Update README.md

README.md

@@ -61,7 +61,7 @@ def generate_response(question: str) -> str:
                            attention_mask=inputs.attention_mask,
                            eos_token_id=tokenizer.eos_token_id,
                            pad_token_id=tokenizer.eos_token_id,
-                           max_new_tokens=256)
+                           max_new_tokens=1024)
         response = tokenizer.batch_decode(outputs.detach().cpu().numpy(), skip_special_tokens=True)[0]
 
         assistant_start = f'''{question} \n assistant\n '''