Update app.py

app.py

@@ -42,7 +42,7 @@ model_x = Qwen2_5_VLForConditionalGeneration.from_pretrained(
     torch_dtype=torch.float16).to(device).eval()
 
 # Load prithivMLmods/WR30a-Deep-7B-0711
-MODEL_ID_T = "prithivMLmods/WR30a-Deep-7B-0711"
+MODEL_ID_T = "NCSOFT/VARCO-VISION-2.0-14B"
 processor_t = AutoProcessor.from_pretrained(MODEL_ID_T, trust_remote_code=True)
 model_t = Qwen2_5_VLForConditionalGeneration.from_pretrained(
     MODEL_ID_T, trust_remote_code=True,
@@ -55,17 +55,6 @@ model_o = Qwen2_5_VLForConditionalGeneration.from_pretrained(
     MODEL_ID_O, trust_remote_code=True,
     torch_dtype=torch.float16).to(device).eval()
 
-#-----------------------------subfolder-----------------------------#
-# Load MonkeyOCR-pro-1.2B
-MODEL_ID_W = "echo840/MonkeyOCR-pro-1.2B"
-SUBFOLDER = "Recognition"
-processor_w = AutoProcessor.from_pretrained(MODEL_ID_W, trust_remote_code=True, subfolder=SUBFOLDER)
-model_w = Qwen2_5_VLForConditionalGeneration.from_pretrained(
-    MODEL_ID_W, trust_remote_code=True,
-    subfolder=SUBFOLDER,
-    torch_dtype=torch.float16).to(device).eval()
-#-----------------------------subfolder-----------------------------#
-
 # Function to downsample video frames
 def downsample_video(video_path):
     """
@@ -110,12 +99,9 @@ def generate_image(model_name: str,
     elif model_name == "Visionary-R1-3B":
         processor = processor_o
         model = model_o
-    elif model_name == "WR30a-Deep-7B-0711":
+    elif model_name == "Varco-Vision-2.0-14B":
         processor = processor_t
         model = model_t
-    elif model_name == "MonkeyOCR-pro-1.2B":
-        processor = processor_w
-        model = model_w
     else:
         yield "Invalid model selected.", "Invalid model selected."
         return
@@ -177,12 +163,9 @@ def generate_video(model_name: str,
     elif model_name == "Visionary-R1-3B":
         processor = processor_o
         model = model_o
-    elif model_name == "WR30a-Deep-7B-0711":
+    elif model_name == "Varco-Vision-2.0-14B":
         processor = processor_t
         model = model_t
-    elif model_name == "MonkeyOCR-pro-1.2B":
-        processor = processor_w
-        model = model_w
     else:
         yield "Invalid model selected.", "Invalid model selected."
         return
@@ -331,11 +314,11 @@ with gr.Blocks(css=css, theme="bethecloud/storj_theme") as demo:
                 #download_btn = gr.Button("Download Result.md")
 
             model_choice = gr.Radio(choices=[
-                 "Camel-Doc-OCR-080125(v2)", "WR30a-Deep-7B-0711",
-                 "ViGaL-7B", "MonkeyOCR-pro-1.2B", "Visionary-R1-3B"
+                 "Camel-Doc-OCR-080125(v2)", "Varco-Vision-2.0-14B",
+                 "ViGaL-7B", "Visionary-R1-3B"
             ],
                                     label="Select Model",
-                                    value="Vision-Matters-7B")
+                                    value="Camel-Doc-OCR-080125(v2)")
 
             gr.Markdown("**Model Info 💻** | [Report Bug](https://huggingface.co/spaces/prithivMLmods/Multimodal-VLMs-5x/discussions)")         
             gr.Markdown("> [Camel-Doc-OCR-080125(v2)](https://huggingface.co/prithivMLmods/WR30a-Deep-7B-0711): the camel-doc-ocr-080125 model is a fine-tuned version of qwen2.5-vl-7b-instruct, optimized for document retrieval, content extraction, and analysis recognition. built on top of the qwen2.5-vl architecture, this model enhances document comprehension capabilities.")