Mahdi Ihdeme's picture

1

Mahdi Ihdeme

mihdeme

·

AI & ML interests

Computer Vision and LLMs

Recent Activity

reacted to prithivMLmods's post with 👍 2 days ago

Try out the demo for Multimodal OCR featuring the implementation of models including `RolmOCR` and `Qwen2VL OCR`. The use case showcases image-text-to-text conversion and video understanding support for the RolmOCR model ! 🚀 🤗Multimodal OCR Space : https://huggingface.co/spaces/prithivMLmods/Multimodal-OCR 📦The models implemented in this Space are: + Qwen2VL OCR : https://huggingface.co/prithivMLmods/Qwen2-VL-OCR-2B-Instruct `[ or ]` + Qwen2VL OCR2 : https://huggingface.co/prithivMLmods/Qwen2-VL-OCR2-2B-Instruct + RolmOCR : https://huggingface.co/reducto/RolmOCR `Qwen2VL OCR supports only image-text-to-text in the space.`

updated a model about 2 months ago

mihdeme/flan-t5-qa

View all activity

Organizations

None yet

models 4

mihdeme/flan-t5-qa

Text2Text Generation • Updated Feb 27 • 11

mihdeme/results

mihdeme/mt-fr-en-tatoeba

Translation • Updated Feb 21 • 9

mihdeme/t5-fr-en-tatoeba

Translation • Updated Feb 20 • 2

datasets

None public yet