Update app.py

app.py

@@ -84,7 +84,7 @@ with gr.Blocks() as demo:
             return_tensors="pt", 
             add_special_tokens=False
         )
-        batch = {k: v.cuda() for k, v in batch.items()}
+        # batch = {k: v.cuda() for k, v in batch.items()} # Using CPU only
         generated = model.generate(batch["input_ids"], max_length=1024, temperature=0.8)
         bot_message = tokenizer.decode(generated[0][:-1]).split("### Assistant:\n", 1)[1]