Upload local_llm.py

models/local_llm.py

@@ -0,0 +1,7 @@
+import subprocess
+
+def run_llm(prompt: str) -> str:
+    result = subprocess.run([
+        "./main", "-m", "models/ggml-model.bin", "-p", prompt, "-n", "128"
+    ], capture_output=True, text=True)
+    return result.stdout