torch

app.py

@@ -1,25 +1,13 @@
 import gradio as gr
 from transformers import Qwen2VLForConditionalGeneration, AutoProcessor
-from transformers import BitsAndBytesConfig
 from util.vision_util import process_vision_info
 import json
 from PIL import Image
-import torch
-
-# Configure 4-bit quantization
-quantization_config = BitsAndBytesConfig(
-    load_in_4bit=True,
-    bnb_4bit_compute_dtype=torch.float16,
-    bnb_4bit_quant_type="nf4",
-    bnb_4bit_use_double_quant=True,
-)
 
 # Load model and processor
 model = Qwen2VLForConditionalGeneration.from_pretrained(
     "datamoon/qwen2-vl-iranian-idcard-ocr",
-    device_map="auto",
-    quantization_config=quantization_config,
-    torch_dtype=torch.float16
+    device_map="auto"
 )
 processor = AutoProcessor.from_pretrained(
     "datamoon/qwen2-vl-iranian-idcard-ocr",