Update app.py

app.py

@@ -11,8 +11,11 @@ from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStream
 MAX_MAX_NEW_TOKENS = 2048
 DEFAULT_MAX_NEW_TOKENS = 1024
 MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096"))
+model = None
+tokenizer = None
 
 def load_model():
+    global model, tokenizer
     model_id = "stabilityai/ar-stablelm-2-chat"
     model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", trust_remote_code=True)
     tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)