Update app.py

app.py

@@ -32,6 +32,8 @@ streamer = TextStreamer(tokenizer)
 
 model = AutoModelForCausalLM.from_pretrained(model, trust_remote_code=True, device_map="cuda")
 model = PeftModel.from_pretrained(model, peft_model)
+
+device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')
 model.to(device)
 
 model = model.eval()