Sayak Paul's picture

Sayak Paul

sayakpaul

·

https://sayak.dev

AI & ML interests

Diffusion models, representation learning

Recent Activity

commented on a paper about 6 hours ago

Radial Attention: $O(n\log n)$ Sparse Attention with Energy Decay for Long Video Generation

upvoted a paper about 6 hours ago

Radial Attention: O(nlog n) Sparse Attention with Energy Decay for Long Video Generation

reacted to burtenshaw's post with ❤️ about 9 hours ago

Inference for generative ai models looks like a mine field, but there’s a simple protocol for picking the best inference: 🌍 95% of users >> If you’re using open (large) models and need fast online inference, then use Inference providers on auto mode, and let it choose the best provider for the model. https://huggingface.co/docs/inference-providers/index 👷 fine-tuners/ bespoke >> If you’ve got custom setups, use Inference Endpoints to define a configuration from AWS, Azure, GCP. https://endpoints.huggingface.co/ 🦫 Locals >> If you’re trying to stretch everything you can out of a server or local machine, use Llama.cpp, Jan, LMStudio or vLLM. https://huggingface.co/settings/local-apps#local-apps 🪟 Browsers >> If you need open models running right here in the browser, use transformers.js. https://github.com/huggingface/transformers.js Let me know what you’re using, and if you think it’s more complex than this.

View all activity

Organizations

upvoted a paper about 6 hours ago

Radial Attention: O(nlog n) Sparse Attention with Energy Decay for Long Video Generation

Paper • 2506.19852 • Published 8 days ago • 18

upvoted an article 10 days ago

Article

(LoRA) Fine-Tuning FLUX.1-dev on Consumer Hardware

By

and 4 others •

14 days ago

• 68

upvoted an article 21 days ago

Article

Mixture of Experts Explained

By

and 5 others •

Dec 11, 2023

• 710

upvoted 2 articles about 1 month ago

Article

How to train a new language model from scratch using Transformers and Tokenizers

By

•

Feb 14, 2020

• 41

Article

Exploring Quantization Backends in Diffusers

By

and 2 others •

May 21

• 37

upvoted 2 articles 2 months ago

Article

Welcoming Llama Guard 4 on Hugging Face Hub

By

and 3 others •

Apr 29

• 38

Article

CinePile 2.0 - making stronger datasets with adversarial refinement

By

and 3 others •

Oct 23, 2024

• 16

upvoted an article 3 months ago

Article

Welcome Llama 4 Maverick & Scout on Hugging Face!

By

and 6 others •

Apr 5

• 145

upvoted 2 papers 3 months ago

A Refined Analysis of Massive Activations in LLMs

Paper • 2503.22329 • Published Mar 28 • 14

ZClip: Adaptive Spike Mitigation for LLM Pre-Training

Paper • 2504.02507 • Published Apr 3 • 89

upvoted a collection 3 months ago

SANA-1.5

SANA-1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer • 6 items • Updated Apr 17 • 6

upvoted an article 3 months ago

Article

Don't repeat yourself - 🤗 Transformers Design Philosophy

By

•

Apr 5, 2022

• 35

upvoted 3 articles 4 months ago

Article

Welcome Gemma 3: Google's all new multimodal, multilingual, long context open LLM

By

and 3 others •

Mar 12

• 439

Article

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

By

and 2 others •

Jun 24, 2024

• 197

Article

Distilling from Dialogues: Finding Meaning in LLM Interactions

By

•

Feb 25

• 4

upvoted a collection 4 months ago

Remote VAE Inference Endpoints

Models and handler code used in https://huggingface.co/blog/remote_vae • 5 items • Updated Mar 10 • 6

upvoted 2 articles 4 months ago

Article

Remote VAEs for decoding with HF endpoints 🤗

By

and 1 other •

Feb 24

• 40

Article

SigLIP 2: A better multilingual vision language encoder

By

and 2 others •

Feb 21

• 169

upvoted a paper 4 months ago

SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features

Paper • 2502.14786 • Published Feb 20 • 145

upvoted a collection 4 months ago

PaliGemma 2 Release

Vision-Language Models available in multiple 3B, 10B and 28B variants. • 32 items • Updated May 30 • 148