Update app.py

app.py

@@ -52,6 +52,7 @@ model = transformers.AutoModelForCausalLM.from_pretrained(
 )
 model.to("cuda")  # Move the model to GPU
 tokenizer = transformers.AutoTokenizer.from_pretrained("Qwen/Qwen2.5-7B-Instruct-AWQ")
+tokenizer.to("cuda")  # Move the tokenizer to GPU
 
 llm = transformers.pipeline(
     task="text-generation",