Update app.py

app.py

@@ -29,9 +29,11 @@ h3 {
 """
 
 device = "cuda" if torch.cuda.is_available() else "cpu"
+# Load the fine-tuned model configuration
+config = AutoConfig.from_pretrained("jwang2373/UW-SBEL-ChronoPhi-4b-it")
 
 tokenizer = AutoTokenizer.from_pretrained(MODEL, trust_remote_code=True)
-model = AutoModelForCausalLM.from_pretrained(MODEL, torch_dtype=torch.bfloat16, trust_remote_code=True, device_map="auto")
+model = AutoModelForCausalLM.from_pretrained(MODEL, torch_dtype=torch.bfloat16, trust_remote_code=True, device_map="auto",config=config)
 model = model.eval()
 
 @spaces.GPU()