Update app.py

app.py

@@ -19,10 +19,10 @@ model = AutoModelForCausalLM.from_pretrained(model_name)
 def generate_text(input_text):
     inputs = tokenizer(input_text, return_tensors="pt")
     #outputs = model.generate(inputs["input_ids"], max_length=256, num_return_sequences=1)
-    output = model.generate(
+    outputs = model.generate(
     inputs["input_ids"],
-    num_return_sequences=1,
     max_length=256,            # Set max length for output
+    num_return_sequences=1,
     temperature=0.8,           # Control randomness (higher is more random)
     top_k=50,                  # Top-k sampling to limit vocabulary to top 50 choices
     top_p=0.95,                # Nucleus sampling to choose tokens with 95% cumulative probability