Mohamed Rashad's picture

Mohamed Rashad PRO

MohamedRashad

·

AI & ML interests

Computer Vision, Robotics, Natural Language Processing

Recent Activity

liked a Space 1 day ago

Remsky/Kokoro-TTS-Zero

reacted to their post with 🚀 6 days ago

The winners of Best Paper Award in NeurIPs2024 (FoundationVision) https://huggingface.co/papers/2404.02905 has just released a new paper called infinty: https://huggingface.co/papers/2412.04431 And i managed to build a space for it so anyone can try it out: https://huggingface.co/spaces/MohamedRashad/Infinity The idea of a text to image model using autoregressive archticture is quite interesting in my opinion.

reacted to alielfilali01's post with 👍 6 days ago

3C3H AraGen Leaderboard welcomes today https://huggingface.co/deepseek-ai/DeepSeek-V3 and 12 other models (including the late gpt-3.5 💀) to the ranking of best LLMs in Arabic ! Observations: - DeepSeek-v3 ranked 3rd and only Open model among the top 5 ! - A 14B open model (https://huggingface.co/Qwen/Qwen2.5-14B-Instruct) outperforms gpt-3.5-turbo-0125 (from last year). This shows how much we came in advancing and supporting Arabic presence within the LLM ecosystem ! - Contrary to what observed in likelihood-acc leaderboards (like https://huggingface.co/spaces/OALL/Open-Arabic-LLM-Leaderboard) further finetuned models like https://huggingface.co/maldv/Qwentile2.5-32B-Instruct actually decreased the performance compared to the original model https://huggingface.co/Qwen/Qwen2.5-32B-Instruct. It's worth to note that the decrease is statiscally insignificant which imply that at best, the out-domain finetuning do not really hurts the model original capabilities acquired during pretraining. Previous work addressed this (finetuning VS pretraining) but more investigation in this regard is required (any PhDs here ? This could be your question ...) Check out the latest rankings: https://huggingface.co/spaces/inceptionai/AraGen-Leaderboard

View all activity

Organizations

MohamedRashad's activity

upvoted an article about 1 month ago

Article

🐺🐦‍⬛ LLM Comparison/Test: 25 SOTA LLMs (including QwQ) through 59 MMLU-Pro CS benchmark runs

By

•

Dec 4, 2024

• 76

upvoted a paper about 2 months ago

Arabic-Nougat: Fine-Tuning Vision Transformers for Arabic OCR and Markdown Extraction

Paper • 2411.17835 • Published Nov 19, 2024 • 3

upvoted a paper 3 months ago

Atlas-Chat: Adapting Large Language Models for Low-Resource Moroccan Arabic Dialect

Paper • 2409.17912 • Published Sep 26, 2024 • 24

upvoted a collection 6 months ago

ArzEn-LLM

Models trained on AraZn Dataset • 16 items • Updated Jul 1, 2024 • 8

upvoted a paper 6 months ago

ArzEn-LLM: Code-Switched Egyptian Arabic-English Translation and Speech Recognition Using LLMs

Paper • 2406.18120 • Published Jun 26, 2024 • 5

upvoted a collection 9 months ago

ZeroGPU Spaces

ZeroGPU Spaces made by the community • 17 items • Updated Jun 6, 2024 • 232