Update app.py

app.py

@@ -87,7 +87,7 @@ def generate(prompt, history):
         # tokenize=True,
         return_dict=True,
         return_tensors="pt",
-    ).to(gpu_model.device)
+    ).to(model.device)
     outputs = model.generate(
         **inputs,
         max_new_tokens=512,