Update README.md

README.md

@@ -95,7 +95,7 @@ model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
 # conduct text completion
 generated_ids = model.generate(
     **model_inputs,
-    max_new_tokens=40960,
+    max_new_tokens=32768,
     temperature=0.6,
     top_p=0.95,
 )