Skip to content
View merveenoyan's full-sized avatar
πŸ€—
building
πŸ€—
building

Block or report merveenoyan

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
merveenoyan/README.md

Banner

Hi πŸ‘‹, I'm Merve

I build, write, showcase around zero-shot vision, multimodality, optimization and more (mostly transformers).

πŸ€— My Hugging Face profile has a lot of cool stuff and I also write blogs on everything cutting-edge over there.

🌱 smol-vision: notebooks, scripts and more on various zero-shot vision/multimodal model optimizations

πŸ”– Vision Language Models Explained πŸ”– Autoencoders Visualized

πŸ”– Introduction to Quantization πŸ”– ConvNets Visualized

πŸ”– PaliGemma – Google's Cutting-Edge Open Vision Language Model

πŸ”– Fine-tuning Florence-2 - Microsoft's Cutting-edge Vision Language Models

▢️ A walkthrough on multimodality, papers, tools and more

▢️ A video on open-source LLMs, where to find them, how to eval and deploy

▢️ A walkthrough on zero-shot vision, papers, tools and more

πŸ”— Let's Connect!

Twitter Medium LinkedIn

Pinned Loading

  1. smol-vision smol-vision Public

    Recipes for shrinking, optimizing, customizing cutting edge vision models. πŸ’œ

    Jupyter Notebook 998 92