Create app.py

app.py

@@ -0,0 +1,20 @@
+import subprocess
+import os
+
+
+
+# Prepare the command
+command = [
+    "python",
+    "run_inference_server.py",
+    "-m", "./models/ggml-model-i2_s.gguf",
+    "--host", "0.0.0.0",
+    "--port", "7860"
+]
+
+# Run it as a subprocess
+try:
+    subprocess.run("ls",check=True)
+    subprocess.run(command, check=True)
+except subprocess.CalledProcessError as e:
+    print(f"Error running inference server: {e}")