remove cuda

app.py

@@ -12,7 +12,7 @@ def chat(text):
 
 if __name__ == '__main__':
     tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True)
-    model = AutoModel.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True).half().cuda()
+    model = AutoModel.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True).half()
     model.eval()
     iface = gr.Interface(fn=chat, inputs="text", outputs="text")
     iface.launch()