Update handler.py

handler.py

@@ -11,10 +11,7 @@ from transformers import AutoModelForVision2Seq, AutoProcessor, BitsAndBytesConf
 model_id = "ibm-granite/granite-vision-3.2-2b"
 
 bnb_config = BitsAndBytesConfig(
-        load_in_4bit=True,
-        bnb_4bit_use_double_quant=True,
-        bnb_4bit_quant_type="nf4",
-        bnb_4bit_compute_dtype=torch.bfloat16,
+        load_in_8bit=True,
         llm_int8_skip_modules=["vision_tower", "lm_head"],
         llm_int8_enable_fp32_cpu_offload=True
 )