Spaces:
Running
on
Zero
Running
on
Zero
Update app.py
Browse files
app.py
CHANGED
@@ -292,12 +292,12 @@ with gr.Blocks(css=css, theme="bethecloud/storj_theme") as demo:
|
|
292 |
model_choice = gr.Radio(
|
293 |
choices=["Camel-Doc-OCR-080125(v2)", "docscopeOCR-7B-050425-exp", "MonkeyOCR-Recognition", "coreOCR-7B-050325-preview"],
|
294 |
label="Select Model",
|
295 |
-
value="
|
296 |
)
|
297 |
gr.Markdown("**Model Info 💻** | [Report Bug](https://huggingface.co/spaces/prithivMLmods/core-OCR/discussions)")
|
298 |
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.")
|
299 |
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.")
|
300 |
-
gr.Markdown("> [
|
301 |
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.")
|
302 |
gr.Markdown(">⚠️note: all the models in space are not guaranteed to perform well in video inference use cases.")
|
303 |
|
|
|
292 |
model_choice = gr.Radio(
|
293 |
choices=["Camel-Doc-OCR-080125(v2)", "docscopeOCR-7B-050425-exp", "MonkeyOCR-Recognition", "coreOCR-7B-050325-preview"],
|
294 |
label="Select Model",
|
295 |
+
value="Camel-Doc-OCR-080125(v2)"
|
296 |
)
|
297 |
gr.Markdown("**Model Info 💻** | [Report Bug](https://huggingface.co/spaces/prithivMLmods/core-OCR/discussions)")
|
298 |
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.")
|
299 |
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.")
|
300 |
+
gr.Markdown("> [Camel-Doc-OCR-080125](https://huggingface.co/prithivMLmods/Camel-Doc-OCR-080125): 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")
|
301 |
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.")
|
302 |
gr.Markdown(">⚠️note: all the models in space are not guaranteed to perform well in video inference use cases.")
|
303 |
|