optional local folder

app.py

@@ -4,9 +4,16 @@ from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline, TextIter
 import time
 import random
 from threading import Thread
+import sys
+import os
 
 # Model configuration - using SmolLM2 for efficient inference
-MODEL_NAME = "HuggingFaceTB/SmolLM2-135M-Instruct"
+# Check for command line argument for local model path
+if len(sys.argv) > 1 and os.path.exists(sys.argv[1]):
+    MODEL_NAME = sys.argv[1]
+    print(f"Using local model from: {MODEL_NAME}")
+else:
+    MODEL_NAME = "HuggingFaceTB/SmolLM2-135M-Instruct"
 
 # Global variables for model components
 tokenizer = None