Update app.py

app.py

@@ -2,11 +2,16 @@ import gradio as gr
 from transformers import AutoModelForCausalLM, AutoTokenizer
 import torch
 
+# Check if CUDA is available
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+if device.type == "cpu":
+    print("Warning: CUDA is not available. Running on CPU, which may be slow.")
+
 # Load the tokenizer and model directly
 model_name = "ruslanmv/ai-medical-model-32bit"
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 model = AutoModelForCausalLM.from_pretrained(model_name)
-model.to("cuda")  # Move model to GPU
+
 
 
 # Function to ask medical questions