Hugging Face's logo
Mohammed Mohammed Ali's picture
16 3

Mohammed Mohammed Ali

MohammedEltoum
Mi6paulino's profile picture
ยท

AI & ML interests

None yet

Recent Activity

reacted to prithivMLmods's post with ๐Ÿ‘ 1 day ago
Dropping Downstream tasks using newly initialized parameters and weights ([classifier.bias & weights]) support domain-specific ๐—ถ๐—บ๐—ฎ๐—ด๐—ฒ ๐—ฐ๐—น๐—ฎ๐˜€๐˜€๐—ถ๐—ณ๐—ถ๐—ฐ๐—ฎ๐˜๐—ถ๐—ผ๐—ป. Based on siglip2-base-patch16-224 and DomainNet (single-domain, multi-source adaptation), with Fashion-MNIST for experimental testing. ๐Ÿงคโ˜„๏ธ 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 ๐Ÿค—. 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 ๐Ÿ‘ 1 day 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 2 days ago
OpenVLThinker: An Early Exploration to Complex Vision-Language Reasoning via Iterative Self-Improvement
View all activity

Organizations

ARIC's profile picture

datasets

None public yet