Update app.py

app.py

@@ -10,9 +10,14 @@ CORS(app)
 # ----------------------------
 # Model (UNGATED, FREE)
 # ----------------------------
-model = "microsoft/phi-3-mini-4k-instruct"
-device = torch.device("cpu")
-model.to(device)
+MODEL_NAME = "microsoft/phi-3-mini-4k-instruct"
+DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
+
+tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
+model = AutoModelForCausalLM.from_pretrained(
+    MODEL_NAME,
+    torch_dtype=torch.float16 if DEVICE == "cuda" else torch.float32
+).to(DEVICE)
 
 # ----------------------------
 # SYSTEM PROMPT