Fix HF Space startup timeout: remove blocking model preload

Downloading Qwen2.5-1.5B + MiniLM before app.launch() blocks the
Gradio server from starting within HF's ~5 min startup timeout.
Models are already lazily loaded on first request via model_loader.py.

app.py

@@ -1,6 +1,5 @@
 import gradio as gr
 import config
-from models.model_loader import get_llm, get_embedder
 from ui.compress_tab import build_compress_tab
 from ui.history_tab import build_history_tab
 
@@ -14,14 +13,8 @@ def build_app() -> gr.Blocks:
 
 
 if __name__ == "__main__":
-    print("Loading models (first run may download weights)...")
-    get_llm()
-    get_embedder()
-
-    print("Starting TinyPress...")
     app = build_app()
     app.launch(
-        share = False,
-        debug = True,
-        server_port = config.SERVER_PORT
+        share=False,
+        server_port=config.SERVER_PORT,
     )