Update app.py

app.py

@@ -398,6 +398,12 @@ with gr.Blocks(css=css, theme="bethecloud/storj_theme") as demo:
                 value="Camel-Doc-OCR-062825"
             )
 
+            gr.Markdown("**Model Info 💻** | [Report Bug](https://huggingface.co/spaces/prithivMLmods/Doc-VLMs-v2-Localization/discussions)")
+            gr.Markdown("> [Camel-Doc-OCR-062825](https://huggingface.co/prithivMLmods/Camel-Doc-OCR-062825) : camel-doc-ocr-062825 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("> [OCRFlux-3B](https://huggingface.co/ChatDOC/OCRFlux-3B) : ocrflux-3b model that's fine-tuned from qwen2.5-vl-3b-instruct using our private document datasets and some data from olmocr-mix-0225 dataset. optimized for document retrieval, content extraction, and analysis recognition. the best way to use this model is via the ocrflux toolkit.")
+            gr.Markdown("> [ViLaSR](https://huggingface.co/AntResearchNLP/ViLaSR) : vilasr-7b model as presented in reinforcing spatial reasoning in vision-language models with interwoven thinking and visual drawing. efficient reasoning capabilities.")
+            gr.Markdown("> [ShotVL-7B](https://huggingface.co/Vchitect/ShotVL-7B) : shotvl-7b is a fine-tuned version of qwen2.5-vl-7b-instruct, trained by supervised fine-tuning on the largest and high-quality dataset for cinematic language understanding to date. it currently achieves state-of-the-art performance on shotbench.")
+
     image_submit.click(
         fn=generate_image,
         inputs=[model_choice, image_query, image_upload, max_new_tokens, temperature, top_p, top_k, repetition_penalty],