Spaces:
Running
on
Zero
Running
on
Zero
Update app.py
Browse files
app.py
CHANGED
@@ -295,9 +295,9 @@ with gr.Blocks(css=css, theme="bethecloud/storj_theme") as demo:
|
|
295 |
value="Lumian-VLR-7B-Thinking"
|
296 |
)
|
297 |
gr.Markdown("**Model Info 💻** | [Report Bug](https://huggingface.co/spaces/prithivMLmods/Multimodal-VLM-Thinking/discussions)")
|
298 |
-
gr.Markdown("> MiniCPM-V 4.0 is the latest efficient model in the MiniCPM-V series. The model is built based on SigLIP2-400M and MiniCPM4-3B with a total of 4.1B parameters. It inherits the strong single-image, multi-image and video understanding performance of MiniCPM-V 2.6 with largely improved efficiency. Lumian-VLR-7B-Thinking is a high-fidelity vision-language reasoning model built on Qwen2.5-VL-7B-Instruct, designed for fine-grained multimodal understanding, video reasoning, and document comprehension through explicit grounded reasoning.")
|
299 |
-
gr.Markdown("> olmOCR-7B-0225-preview is a 7B parameter open large model designed for OCR tasks with robust text extraction, especially in complex document layouts. Typhoon-ocr-3b is a 3B parameter OCR model optimized for efficient and accurate optical character recognition in challenging conditions.")
|
300 |
-
gr.Markdown("> DREX-062225-exp is an experimental multimodal model emphasizing strong document reading and extraction capabilities combined with vision-language understanding to support detailed document parsing and reasoning tasks.")
|
301 |
gr.Markdown("> ⚠️ Note: Video inference performance can vary significantly between models.")
|
302 |
|
303 |
image_submit.click(
|
|
|
295 |
value="Lumian-VLR-7B-Thinking"
|
296 |
)
|
297 |
gr.Markdown("**Model Info 💻** | [Report Bug](https://huggingface.co/spaces/prithivMLmods/Multimodal-VLM-Thinking/discussions)")
|
298 |
+
gr.Markdown("> [MiniCPM-V 4.0](https://huggingface.co/openbmb/MiniCPM-V-4) is the latest efficient model in the MiniCPM-V series. The model is built based on SigLIP2-400M and MiniCPM4-3B with a total of 4.1B parameters. It inherits the strong single-image, multi-image and video understanding performance of MiniCPM-V 2.6 with largely improved efficiency. [Lumian-VLR-7B-Thinking](https://huggingface.co/prithivMLmods/Lumian-VLR-7B-Thinking) is a high-fidelity vision-language reasoning model built on Qwen2.5-VL-7B-Instruct, designed for fine-grained multimodal understanding, video reasoning, and document comprehension through explicit grounded reasoning.")
|
299 |
+
gr.Markdown("> [olmOCR-7B-0225-preview](https://huggingface.co/allenai/olmOCR-7B-0225-preview) is a 7B parameter open large model designed for OCR tasks with robust text extraction, especially in complex document layouts. [Typhoon-ocr-3b](https://huggingface.co/scb10x/typhoon-ocr-3b) is a 3B parameter OCR model optimized for efficient and accurate optical character recognition in challenging conditions.")
|
300 |
+
gr.Markdown("> [DREX-062225-exp](https://huggingface.co/prithivMLmods/DREX-062225-exp) is an experimental multimodal model emphasizing strong document reading and extraction capabilities combined with vision-language understanding to support detailed document parsing and reasoning tasks.")
|
301 |
gr.Markdown("> ⚠️ Note: Video inference performance can vary significantly between models.")
|
302 |
|
303 |
image_submit.click(
|