Update README.md

README.md

@@ -127,7 +127,7 @@ inputs = {k: v.to(model.device) for k, v in inputs.items()}
 # generate output
 with torch.inference_mode():
     with torch.autocast("cuda", enabled=True, dtype=torch.bfloat16):
-        generated_ids = model.generate(**inputs, max_new_tokens=256)
+        generated_ids = model.generate(**inputs, max_new_tokens=512)
 
 # only get generated tokens; decode them to text
 generated_tokens = generated_ids[:, inputs['input_ids'].size(1):]