sayakpaul - Overview (original) (raw)
Learn, unlearn and relearn.
Sayak Paul sayakpaul
Learn, unlearn and relearn.
- India
- https://sayak.dev
- X @RisingSayak
Organizations
Block or report sayakpaul
My name is Sayak Paul! ๐พ
- ๐ญ I work on ๐งจ diffusion models at Hugging Face ๐ค
- ๐ฑ Iโm interested in the area of representation learning.
- ๐ฏ Iโm always open to meaningful collaborations.
- โก Fun fact: I love watching crime and action thrillers (The Silence of the Lambs being an all-time favorite one).
- ๐ Recepient of the Google Open Source Peer Bonus Award (2020, 2021, and 2022). Also received the TensorFlow Top Contributor Award 2021.
- ๐ซ More details - sayak.dev.
Following are some of my favorite repositories that I have contributed to and/or contribute to.
Pinned Loading
- ๐ค Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch and FLAX.
Python 29.3k 6k - Code for instruction-tuning Stable Diffusion.
Python 233 19 - Scalable and memory-optimized training of diffusion models
Python 1.2k 127 - Probing the representations of Vision Transformers.
Jupyter Notebook 326 21 - This project shows how to serve an ONNX-optimized image classification model as a web service with FastAPI, Docker, and Kubernetes.
Jupyter Notebook 216 39 - Just another reasonably minimal repo for class-conditional training of pixel-space diffusion transformers.
Python 97 8