Update app.py

app.py

@@ -19,7 +19,7 @@ MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096"))
 if torch.cuda.is_available():
     model_id = "BenBranyon/zephyr-sumbot-all-songs-split"
     model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")
-    tokenizer = AutoTokenizer.from_pretrained("stabilityai/stablelm-zephyr-3b")
+    tokenizer = AutoTokenizer.from_pretrained(model_id)
     tokenizer.use_default_system_prompt = False
 
 #Inference API Code