Update app.py

app.py

@@ -9,7 +9,6 @@ from threading import Thread
 
 HF_TOKEN = os.environ.get("HF_TOKEN", None)
 MODEL_ID = "ehristoforu/SoRu-0008"
-MODELS = os.environ.get("MODELS")
 MODEL_NAME = MODELS.split("/")[-1]
 
 TITLE = "<h1><center>Qwen2-7B-instruct</center></h1>"
@@ -37,11 +36,11 @@ text-align: center;
 """
 
 model = AutoModelForCausalLM.from_pretrained(
-          MODELS,
+          MODEL_ID,
           torch_dtype=torch.float16,
           device_map="auto",
         )
-tokenizer = Qwen2Tokenizer.from_pretrained(MODELS)
+tokenizer = Qwen2Tokenizer.from_pretrained(MODEL_ID)
 
 @spaces.GPU
 def stream_chat(message: str, history: list, temperature: float, max_new_tokens: int, top_p: float, top_k: int, penalty: float):