Update model.py

model.py

@@ -14,7 +14,7 @@ tokenizer = AutoTokenizer.from_pretrained(model_id, use_fast=True)
 model = AutoGPTQForCausalLM.from_quantized(model_id,
         use_safetensors=True,
         trust_remote_code=False,
-        device="cuda",
+        device="cuda:0",
         use_triton=False,
         quantize_config=None)