prithivMLmods commited on
Commit
4b859d8
·
verified ·
1 Parent(s): a9b3d11

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +6 -0
app.py CHANGED
@@ -274,6 +274,12 @@ with gr.Blocks(css=css, theme="bethecloud/storj_theme") as demo:
274
  value="SkyCaptioner-V1"
275
  )
276
 
 
 
 
 
 
 
277
  image_submit.click(
278
  fn=generate_image,
279
  inputs=[model_choice, image_query, image_upload, max_new_tokens, temperature, top_p, top_k, repetition_penalty],
 
274
  value="SkyCaptioner-V1"
275
  )
276
 
277
+ gr.Markdown("**Model Info**")
278
+ gr.Markdown("⤷ [SkyCaptioner-V1](https://huggingface.co/Skywork/SkyCaptioner-V1): structural video captioning model designed to generate high-quality, structural descriptions for video data. It integrates specialized sub-expert models.")
279
+ gr.Markdown("⤷ [SpaceThinker-Qwen2.5VL-3B](https://huggingface.co/remyxai/SpaceThinker-Qwen2.5VL-3B): thinking/reasoning multimodal/vision-language model (VLM) trained to enhance spatial reasoning.")
280
+ gr.Markdown("⤷ [coreOCR-7B-050325-preview](https://huggingface.co/prithivMLmods/coreOCR-7B-050325-preview): model is a fine-tuned version of qwen/qwen2-vl-7b, optimized for document-level optical character recognition (ocr), long-context vision-language understanding.")
281
+ gr.Markdown("⤷ [Imgscope-OCR-2B-0527](https://huggingface.co/prithivMLmods/Imgscope-OCR-2B-0527): fine-tuned version of qwen2-vl-2b-instruct, specifically optimized for messy handwriting recognition, document ocr, realistic handwritten ocr, and math problem solving with latex formatting.")
282
+
283
  image_submit.click(
284
  fn=generate_image,
285
  inputs=[model_choice, image_query, image_upload, max_new_tokens, temperature, top_p, top_k, repetition_penalty],