Pinned
Had the honor to present diffusion transformers at CS25, Stanford. The place is truly magical.
Slides: bit.ly/dit-cs25
Recording: youtu.be/vXtapCFctTI?si…
Thanks to @stevenyfeng for making it happen!
Sayak Paul
6,926 posts
- . @DeepMind released this GOLD a couple days back. If you ever wanted to study Transformers from scratch I think this would be that one resource you wouldn't want to miss:
- What do the Vision Transformers learn? How do they encode anything useful for image recognition? In our latest work, we reimplement a number of works done in this area & investigate various ViT model families (DeiT, DINO, original, etc.). Done w/ @ariG23498 1/
GIF - The Tiny Recursive Model codebase is a piece of art 🖼️ If you're into reading code more than writing it, you should check it out!
- It's possible to use @MSFTResearch's `interpret` to *interpret* `keras` model. `interpret` + @TensorFlow 2.0 = too much awesomeness. Check this notebook I made for ya: bit.ly/2JMBIYR #DeepLearning #TensorFlow
00:00 - . @AshwiniVaishnaw why are you recruiting folks who don't have a solid technical know-how of AI systems are built at a large scale? Stop going via only academic affiliation & look at the actual hands-on stuff (core contributions to good libs, knowledge across the AI spectrum,
- For the ones that do not know, I maintain a list of resources for the people willing to learn @TensorFlow 2.0. Currently, the list looks like so & can be accessed here: github.com/sayakpaul/TF-2…. Please feel free to pass along any suggestions regarding new resources :)
- New project 📢 We show how to deploy a deep learning model with Docker + Kubernetes + GitHub Actions. We show this with two promising candidates - FastAPI (for REST) and TF Serving (for gRPC). 1/
- Fine-tuning 5B param video models should be possible with a SINGLE 24GB GPU 🍓 We're releasing CogVideoX-Factory, a repository containing memory-optimized scripts to fine-tune Cog family of video models for T2V and I2V 🧪 github.com/a-r-r-o-w/cogv…
00:00 - @TensorFlow model -> 38 MB, val_accuracy: 97.5% #TF Lite model -> *3.4 MB*, val_accuracy: ~96% I'll just leave it there. Notebook: colab.research.google.com/drive/1hXfJfa8… @GoogleDevsIN @GoogleDevExpert
- Reading clean Python code to improve Python skills is underrated.
- I am preparing this list as a central repository which enlists resources to learn about @TensorFlow 2.0. If you would like to add your recommendations reach out to me directly via sayak.dev. @GoogleDevExpert @GoogleDevsIN @GoogleAI @googledevs
- Shubho Deepaboli! Today, I am delighted to announce that I am joining the mighty forces at @huggingface as a Developer Advocate Engineer! Working on ensuring developers benefit from our ML tooling is heavy-weight and full of opportunities.
