I build, write, showcase around zero-shot vision, multimodality, optimization and more (mostly transformers).
๐ค My Hugging Face profile has a lot of cool stuff and I also write blogs on everything cutting-edge over there.
๐ฑ smol-vision: notebooks, scripts and more on various zero-shot vision/multimodal model optimizations
๐ Fine-tuning Florence-2 - Microsoft's Cutting-edge Vision Language Models
๐ Vision Language Models Explained
๐ PaliGemma โ Google's Cutting-Edge Open Vision Language Model
๐ Introduction to Quantization