Update app.py

app.py

@@ -6,6 +6,10 @@ import torch
 import spaces
 from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
 
+MODEL_LIST = ["LGAI-EXAONE/EXAONE-3.0-7.8B-Instruct"]
+HF_TOKEN = os.environ.get("HF_TOKEN", None)
+MODEL = os.environ.get("MODEL_ID")
+
 DESCRIPTION = """ EXAONE-3.0-7.8B-Instruct Official Demo \
 """
 
@@ -15,10 +19,9 @@ MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "3840"))
 
 device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
 
-model_id = "LGAI-EXAONE/EXAONE-3.0-7.8B-Instruct"
-tokenizer = AutoTokenizer.from_pretrained(model_id)
+tokenizer = AutoTokenizer.from_pretrained(MODEL)
 model = AutoModelForCausalLM.from_pretrained(
-    model_id,
+    MODEL,
     torch_dtype=torch.bfloat16,
     trust_remote_code=True,
     device_map="auto",