Update app.py

app.py

@@ -21,7 +21,7 @@ prompt = [
 
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 
-inputs = tokenizer.apply_chat_template(prompt, tokenize=True, add_generation_prompt=True, return_tensors="pt").cuda()
+inputs = tokenizer.apply_chat_template(prompt, tokenize=True, add_generation_prompt=True, return_tensors="pt") #.cuda()
 
 model = AutoModelForCausalLM.from_pretrained(
   model_id,