Update app.py

app.py

@@ -140,7 +140,8 @@ def initialize_model():
     """Initialize the model with appropriate configurations"""
     quantization_config = BitsAndBytesConfig(
         load_in_4bit=True,
-        bnb_4bit_compute_dtype=torch.float8,
+        bnb_4bit_compute_dtype=torch.bfloat16,
+        bnb_4bit_quant_type="nf4",
         bnb_4bit_use_double_quant=True
     )