test2

app.py

@@ -10,7 +10,7 @@ vicuna_tokenizer = AutoTokenizer.from_pretrained("lmsys/vicuna-7b-v1.3")
 # Define the function for generating responses
 def generate_response(model, tokenizer, prompt):
     inputs = tokenizer(prompt, return_tensors="pt")
-    outputs = model.generate(**inputs, max_length=1000, pad_token_id=tokenizer.eos_token_id)
+    outputs = model.generate(**inputs, max_length=500, pad_token_id=tokenizer.eos_token_id)
     response = tokenizer.decode(outputs[0])
     return response