Update app.py

app.py

@@ -9,7 +9,7 @@ import torch
 torch.cuda.empty_cache()
 
 # Load the model and tokenizer on CPU
-model = AutoModel.from_pretrained('openbmb/MiniCPM-Llama3-V-2_5-int4', trust_remote_code=True).to('cpu')
+model = AutoModel.from_pretrained('openbmb/MiniCPM-Llama3-V-2_5-int4', trust_remote_code=True)
 tokenizer = AutoTokenizer.from_pretrained('openbmb/MiniCPM-Llama3-V-2_5-int4', trust_remote_code=True)
 model.eval()