Update app.py

app.py

@@ -30,7 +30,7 @@ if st.button("Generate Output"):
                      return_attention_mask=False,
                      padding=True,
                      truncation=True)
-    result = inference_model.generate(**input, repetition_penalty=1.2, max_length=1024)
+    result = model.generate(**input, repetition_penalty=1.2, max_length=1024)
     output = tokenizer.batch_decode(result, skip_special_tokens=True)[0]
     st.text("Generated Result:")
     st.write(output)