Update app.py

app.py

@@ -27,9 +27,9 @@ def initialize_model_once():
         if MODEL_CACHE["model"] is None:
             # Load Phi-2 model (smaller than Mistral)
             MODEL_CACHE["model"] = CTransformers(
-                model="TheBloke/phi-2-GGUF",
-                model_file="phi-2.Q4_K_M.gguf",
-                model_type="Phi2",
+                model="TheBloke/TinyLlama-1.1B-Chat-v1.0-GGUF",
+                model_file="tinyllama-1.1b-chat-v1.0.Q4_K_M.gguf",
+                model_type="llama",
                 max_new_tokens=512,
                 temperature=0.1,
                 top_p=0.9,