Update app.py

app.py

@@ -1,17 +1,24 @@
 import gradio as gr
 from transformers import AutoTokenizer, AutoModelForCausalLM
 import torch
+import spaces
 
 model_id = "microsoft/phi-2"
 
+# 🌟 Auto-detect device (CPU/GPU)
+device = "cuda"
+precision = torch.float16
+
 # Load model and tokenizer (CPU + float32)
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 model = AutoModelForCausalLM.from_pretrained(
     model_id,
-    torch_dtype=torch.float32
-).to("cpu")
+    torch_dtype=precision
+).to(device)
+
 
 # Chat function
+@spaces.GPU
 def chat_with_bot(user_input, history):
     history = history or []
     prompt = ""