prithivMLmods commited on
Commit
fbc860a
·
verified ·
1 Parent(s): 921211a

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +2 -2
app.py CHANGED
@@ -258,15 +258,15 @@ with gr.Blocks(css=css, theme="bethecloud/storj_theme") as demo:
258
  with gr.Column():
259
  output = gr.Textbox(label="Output", interactive=False, lines=2, scale=2)
260
  model_choice = gr.Radio(
261
- choices=["docscopeOCR-7B-050425-exp", "coreOCR-7B-050325-preview", "MonkeyOCR"],
262
  label="Select Model",
263
  value="docscopeOCR-7B-050425-exp"
264
  )
265
 
266
  gr.Markdown("**Model Info**")
267
  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.")
268
- 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.")
269
  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.")
 
270
 
271
  image_submit.click(
272
  fn=generate_image,
 
258
  with gr.Column():
259
  output = gr.Textbox(label="Output", interactive=False, lines=2, scale=2)
260
  model_choice = gr.Radio(
261
+ choices=["docscopeOCR-7B-050425-exp", "MonkeyOCR", "coreOCR-7B-050325-preview"],
262
  label="Select Model",
263
  value="docscopeOCR-7B-050425-exp"
264
  )
265
 
266
  gr.Markdown("**Model Info**")
267
  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.")
 
268
  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.")
269
+ 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.")
270
 
271
  image_submit.click(
272
  fn=generate_image,