Update app.py

app.py

@@ -40,7 +40,7 @@ model = AutoModelForCausalLM.from_pretrained(
           torch_dtype=torch.float16,
           device_map="auto",
         )
-tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
+tokenizer = AutoTokenizer.from_pretrained('qnguyen3/WitchLM-1.5B')
 
 @spaces.GPU
 def stream_chat(message: str, history: list, temperature: float, max_new_tokens: int, top_p: float, top_k: int, penalty: float):