Update app.py

app.py

@@ -63,12 +63,12 @@ torch.cuda.empty_cache()
 # Load mô hình Qwen2.5-VL với quantization 4-bit
 model_id = "prithivMLmods/Camel-Doc-OCR-062825"
 
-bnb_config = BitsAndBytesConfig(
-    load_in_4bit=True,
-    bnb_4bit_use_double_quant=True,
-    bnb_4bit_quant_type="nf4",
-    bnb_4bit_compute_dtype=torch.float16
-)
+# bnb_config = BitsAndBytesConfig(
+#     load_in_4bit=True,
+#     bnb_4bit_use_double_quant=True,
+#     bnb_4bit_quant_type="nf4",
+#     bnb_4bit_compute_dtype=torch.float16
+# )
 
 processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)
 model = Qwen2_5_VLForConditionalGeneration.from_pretrained(