Update app.py

app.py

@@ -66,8 +66,8 @@ model_g = Qwen2_5_VLForConditionalGeneration.from_pretrained(
 ).to(device).eval()
 #-----------------------------subfolder-----------------------------#
 
-# Load Perseus-Doc-vl-071225
-MODEL_ID_O = "prithivMLmods/Perseus-Doc-vl-071225"
+# Load Perseus-Doc-vl-0712
+MODEL_ID_O = "prithivMLmods/Perseus-Doc-vl-0712"
 processor_o = AutoProcessor.from_pretrained(MODEL_ID_O, trust_remote_code=True)
 model_o = Qwen2_5_VLForConditionalGeneration.from_pretrained(
     MODEL_ID_O,
@@ -116,7 +116,7 @@ def generate_image(model_name: str, text: str, image: Image.Image,
     elif model_name == "MonkeyOCR-Recognition":
         processor = processor_g
         model = model_g
-    elif model_name == "Perseus-Doc-vl-071225":
+    elif model_name == "Perseus-Doc-vl-0712":
         processor = processor_o
         model = model_o
     else:
@@ -174,7 +174,7 @@ def generate_video(model_name: str, text: str, video_path: str,
     elif model_name == "MonkeyOCR-Recognition":
         processor = processor_g
         model = model_g
-    elif model_name == "Perseus-Doc-vl-071225":
+    elif model_name == "Perseus-Doc-vl-0712":
         processor = processor_o
         model = model_o
     else:
@@ -290,14 +290,14 @@ with gr.Blocks(css=css, theme="bethecloud/storj_theme") as demo:
                     markdown_output = gr.Markdown(label="(Result.Md)")
                     
             model_choice = gr.Radio(
-                choices=["docscopeOCR-7B-050425-exp", "MonkeyOCR-Recognition", "coreOCR-7B-050325-preview", "Perseus-Doc-vl-071225"],
+                choices=["docscopeOCR-7B-050425-exp", "MonkeyOCR-Recognition", "coreOCR-7B-050325-preview", "Perseus-Doc-vl-0712"],
                 label="Select Model",
                 value="docscopeOCR-7B-050425-exp"
             )
             gr.Markdown("**Model Info 💻** | [Report Bug](https://huggingface.co/spaces/prithivMLmods/core-OCR/discussions)")
             gr.Markdown("> [docscopeOCR-7B-050425-exp](https://huggingface.co/prithivMLmods/docscopeOCR-7B-050425-exp): The docscopeOCR-7B-050425-exp model is a fine-tuned version of Qwen2.5-VL-7B-Instruct, optimized for Document-Level Optical Character Recognition (OCR), long-context vision-language understanding, and accurate image-to-text conversion with mathematical LaTeX formatting.")
             gr.Markdown("> [MonkeyOCR](https://huggingface.co/echo840/MonkeyOCR): MonkeyOCR adopts a Structure-Recognition-Relation (SRR) triplet paradigm, which simplifies the multi-tool pipeline of modular approaches while avoiding the inefficiency of using large multimodal models for full-page document processing.")
-            gr.Markdown("> [Perseus-Doc-vl-071225](https://huggingface.co/prithivMLmods/Pollux-OCR-Caption-2B):  The Pollux-OCR-Caption-2B model is a fine-tuned version of Qwen2.5-VL architecture, optimized for Document Retrieval, Content Extraction, and Analysis Recognition. Built on top of the Qwen2.5-VL architecture.")
+            gr.Markdown("> [Perseus-Doc-vl-0712](https://huggingface.co/prithivMLmods/Perseus-Doc-vl-0712): The Perseus-Doc-vl-0712 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")
             gr.Markdown("> [coreOCR-7B-050325-preview](https://huggingface.co/prithivMLmods/coreOCR-7B-050325-preview): The coreOCR-7B-050325-preview model is a fine-tuned version of Qwen2-VL-7B, optimized for Document-Level Optical Character Recognition (OCR), long-context vision-language understanding, and accurate image-to-text conversion with mathematical LaTeX formatting.")
             gr.Markdown(">⚠️note: all the models in space are not guaranteed to perform well in video inference use cases.")