Mohammed Mohammed Ali's picture

16 3

Mohammed Mohammed Ali

MohammedEltoum

·

AI & ML interests

None yet

Recent Activity

reacted to prithivMLmods's post with 👍 2 days ago

Dropping Downstream tasks using newly initialized parameters and weights ([classifier.bias & weights]) support domain-specific 𝗶𝗺𝗮𝗴𝗲 𝗰𝗹𝗮𝘀𝘀𝗶𝗳𝗶𝗰𝗮𝘁𝗶𝗼𝗻. Based on siglip2-base-patch16-224 and DomainNet (single-domain, multi-source adaptation), with Fashion-MNIST for experimental testing. 🧤☄️ Fashion-Mnist : https://huggingface.co/prithivMLmods/Fashion-Mnist-SigLIP2 Multisource-121 : https://huggingface.co/prithivMLmods/Multisource-121-DomainNet Painting-126 : https://huggingface.co/prithivMLmods/Painting-126-DomainNet Sketch-126 : https://huggingface.co/prithivMLmods/Sketch-126-DomainNet Clipart-126 : https://huggingface.co/prithivMLmods/Clipart-126-DomainNet Models are trained with different parameter settings for experimental purposes only, with the intent of further development. Refer to the model page below for instructions on running it with Transformers 🤗. Collection : https://huggingface.co/collections/prithivMLmods/domainnet-0324-67e0e3c934c03cc40c6c8782 Citations : SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features https://arxiv.org/pdf/2502.14786 & Moment Matching for Multi-Source Domain Adaptation : https://arxiv.org/pdf/1812.01754

reacted to hanzla's post with 👍 2 days ago

Hi community, Few days back, I posted about my ongoing research on making reasoning mamba models and I found great insights from the community. Today, I am announcing an update to the model weights. With newer checkpoints, the Falcon3 Mamba R1 model now outperforms very large transformer based LLMs (including Gemini) for Formal Logic questions of MMLU. It scores 60% on formal logic which is considered a tough subset of questions in MMLU. I would highly appreciate your insights and suggestions on this new checkpoint. Model Repo: https://huggingface.co/hanzla/Falcon3-Mamba-R1-v0 Chat space: https://huggingface.co/spaces/hanzla/Falcon3MambaReasoner

upvoted a paper 4 days ago

OpenVLThinker: An Early Exploration to Complex Vision-Language Reasoning via Iterative Self-Improvement

View all activity

Organizations

MohammedEltoum's activity

liked a Space 28 days ago

The Essential AI Toolkit

A curated collection of AI tools for journalists & creators

liked a Space 6 months ago

Ovis1.6 Gemma2 9B

Chat with an AI that understands images and text

liked a model over 1 year ago

timbrooks/instruct-pix2pix

Image-to-Image • Updated Jul 5, 2023 • 171k • • 1.09k