Update app.py

app.py

@@ -88,7 +88,7 @@ def vanilla_chatbot(message, history):
         #print(context)
     prompt = prompt_template_w_context(context, message)
     inputs = tokenizer(prompt, return_tensors="pt")
-    outputs = model.generate(input_ids=inputs["input_ids"].to("cuda"), max_new_tokens=280)
+    outputs = model.generate(input_ids=inputs["input_ids"], max_new_tokens=280)
     #print(tokenizer.batch_decode(outputs)[0])
     #conversation = pipe(message, temperature=0.1)
     ot=tokenizer.batch_decode(outputs)[0]