Update app.py

app.py

@@ -9,6 +9,7 @@ from PIL import Image
 import cv2
 from transformers import (
     Qwen2_5_VLForConditionalGeneration,
+    Qwen2VLForConditionalGeneration,
     AutoProcessor,
     TextIteratorStreamer,
 )
@@ -41,7 +42,7 @@ model_x = Qwen2_5_VLForConditionalGeneration.from_pretrained(
     torch_dtype=torch.float16
 ).to(device).eval()
 
-# Load OCRFlux-3B
+# Load Megalodon-OCR-Sync-0713
 MODEL_ID_T = "prithivMLmods/Megalodon-OCR-Sync-0713"
 processor_t = AutoProcessor.from_pretrained(MODEL_ID_T, trust_remote_code=True)
 model_t = Qwen2_5_VLForConditionalGeneration.from_pretrained(
@@ -51,9 +52,9 @@ model_t = Qwen2_5_VLForConditionalGeneration.from_pretrained(
 ).to(device).eval()
 
 # Load ShotVL-7B
-MODEL_ID_S = "Vchitect/ShotVL-7B"
+MODEL_ID_S = "prithivMLmods/Qwen2-VL-OCR-2B-Instruct"
 processor_s = AutoProcessor.from_pretrained(MODEL_ID_S, trust_remote_code=True)
-model_s = Qwen2_5_VLForConditionalGeneration.from_pretrained(
+model_s = Qwen2VLForConditionalGeneration.from_pretrained(
     MODEL_ID_S,
     trust_remote_code=True,
     torch_dtype=torch.float16
@@ -98,7 +99,7 @@ def generate_image(model_name: str, text: str, image: Image.Image,
     elif model_name == "Megalodon-OCR-Sync-0713":
         processor = processor_t
         model = model_t
-    elif model_name == "ShotVL-7B":
+    elif model_name == "Qwen2-VL-OCR-2B":
         processor = processor_s
         model = model_s
     else:
@@ -154,7 +155,7 @@ def generate_video(model_name: str, text: str, video_path: str,
     elif model_name == "Megalodon-OCR-Sync-0713":
         processor = processor_t
         model = model_t
-    elif model_name == "ShotVL-7B":
+    elif model_name == "Qwen2-VL-OCR-2B":
         processor = processor_s
         model = model_s
     else:
@@ -271,12 +272,28 @@ with gr.Blocks(css=css, theme="bethecloud/storj_theme") as demo:
                     markdown_output = gr.Markdown(label="(Result.md)")
 
             model_choice = gr.Radio(
-                choices=["Camel-Doc-OCR-062825", "MonkeyOCR-pro-1.2B", "Megalodon-OCR-Sync-0713", "ShotVL-7B"],
+                choices=["Camel-Doc-OCR-062825", "MonkeyOCR-pro-1.2B", "Megalodon-OCR-Sync-0713", "Qwen2-VL-OCR-2B"],
                 label="Select Model",
                 value="Camel-Doc-OCR-062825"
             )
 
             gr.Markdown("**Model Info 💻** | [Report Bug](https://huggingface.co/spaces/prithivMLmods/Multimodal-OCR-Comparator/discussions)")
 
+    # Define the submit button actions
+    image_submit.click(fn=generate_image,
+                       inputs=[
+                           model_choice, image_query, image_upload,
+                           max_new_tokens, temperature, top_p, top_k,
+                           repetition_penalty
+                       ],
+                       outputs=[output, markdown_output])
+    video_submit.click(fn=generate_video,
+                       inputs=[
+                           model_choice, video_query, video_upload,
+                           max_new_tokens, temperature, top_p, top_k,
+                           repetition_penalty
+                       ],
+                       outputs=[output, markdown_output])
+
 if __name__ == "__main__":
     demo.queue(max_size=30).launch(share=True, mcp_server=True, ssr_mode=False, show_error=True)