Update app.py

app.py

@@ -55,10 +55,9 @@ def generate(
     stream = model.generate(inputs, **generate_kwargs)
     output = ""
 
-    for response in stream:
-        output += response.token.text
-        yield output
-    return output
+    decoded = tokenizer.batch_decode(generated_ids)
+    print(decoded[0])
+    return decoded[0]
 
 
 additional_inputs=[