Update app.py

app.py

@@ -1,6 +1,6 @@
 import gradio as gr
-from transformers import Qwen2VLForConditionalGeneration, AutoProcessor
-from qwen_vl_utils import process_vision_info
+from transformers import AutoModelForConditionalGeneration, AutoProcessor
+from huggingface_hub import hf_api
 import torch
 import pandas as pd
 import pytesseract
@@ -9,19 +9,16 @@ import cv2
 # Set Tesseract command (only works if Tesseract is already installed on the hosting server)
 pytesseract.pytesseract_cmd = r'/usr/bin/tesseract'
 
-# Check if GPU is available, and use it if possible
-device = "cuda" if torch.cuda.is_available() else "cpu"
+# Initialize the model and processor from Hugging Face Hub
+model_name = "Qwen/Qwen2-VL-2B-Instruct-AWQ"
 
-# Initialize the model and processor
-try:
-    model = Qwen2VLForConditionalGeneration.from_pretrained(
-        "Qwen/Qwen2-VL-2B-Instruct-AWQ",
-        torch_dtype="auto"
-    )
-    model.to(device)  # Move the model to the selected device (CPU or GPU)
-    processor = AutoProcessor.from_pretrained("Qwen/Qwen2-VL-2B-Instruct-AWQ")
-except Exception as e:
-    print(f"Error loading model: {e}")
+model = AutoModelForConditionalGeneration.from_pretrained(
+    model_name,
+    torch_dtype="auto"
+)
+model.to("cpu")
+
+processor = AutoProcessor.from_pretrained(model_name)
 
 # Preprocessing image for OCR
 def preprocess_image(image_path):
@@ -53,11 +50,10 @@ def process_image(image_path):
             ]
         }]
 
-        # Process the vision info and prepare inputs
         text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
         image_inputs, video_inputs = process_vision_info(messages)
         inputs = processor(text=[text], images=image_inputs, videos=video_inputs, padding=True, return_tensors="pt")
-        inputs = inputs.to(device)
+        inputs = inputs.to(model.device)
 
         generated_ids = model.generate(**inputs, max_new_tokens=128)
         output_text = processor.batch_decode(generated_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)