Update app.py

app.py

@@ -63,7 +63,7 @@ def reply(modelA, modelB, prompt):
     responseA = run_inference(pipeA, prompt)    
     pipeB = pipeline("text-generation", model=models_and_tokenizers[modelB][0], tokenizer=models_and_tokenizers[modelB][1], max_new_tokens=512, repetition_penalty=1.5, temperature=0.5, device_map="auto")
     responseB = run_inference(pipeB, prompt)    
-    return responseA[0]["generated_text"], responseB[0]["generated_text"]
+    return responseA, responseB
 
 modelA_dropdown = gr.Dropdown(models_checkpoints, label="Model A", info="Choose the first model for the battle!")
 modelB_dropdown = gr.Dropdown(models_checkpoints, label="Model B", info="Choose the second model for the battle!")