Update app.py with improved Gradio interface and change model's torch_dtype to float32

app.py

@@ -3,10 +3,10 @@ import torch
 from PIL import Image
 from transformers import AutoModel, AutoTokenizer
 
-device = "cuda" if torch.cuda.is_available() else "cpu"
+device = "cpu" 
 
 # Load the model
-model = AutoModel.from_pretrained("openbmb/MiniCPM-Llama3-V-2_5", trust_remote_code=True, torch_dtype=torch.float16)
+model = AutoModel.from_pretrained("openbmb/MiniCPM-Llama3-V-2_5", trust_remote_code=True, torch_dtype=torch.float32)
 model = model.to(device=device)
 
 # Load the tokenizer