Update app.py

app.py

@@ -17,7 +17,7 @@ model = AutoModelForCausalLM.from_pretrained( model_path)
 
 device = 'cpu' # 'cuda'
 @spaces.GPU
-def generate_text(prompt, temperature=0.9, max_length=1200):
+def generate_text(prompt, temperature=0.9, max_length=200):
     # Encode the inputs
     inputs = tokenizer.encode(prompt, return_tensors="pt")
     attention_mask = torch.ones(inputs.shape, dtype=torch.long)