Links for February 11th

Here are some links I found interesting this week.

[1909.08053] Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism

Introduction | CS324

Deep Learning 101: Transformer Activation Functions Explainer - Sigmoid, ReLU, GELU, Swish — Salt Data Labs

Transformers from scratch | peterbloem.nl

Generative Modeling with Sparse Transformers

Generative Modeling by Estimating Gradients of the Data Distribution | Yang Song

Metropolis-adjusted Langevin algorithm - Wikipedia

React iOS Corners

[2205.14135] FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness

Simulators - LessWrong

Underutilized Fixed Assets - kwokchain

(1) 【ENG SUB】Nirvana In Fire Ep1 【HD】 Welcome to subscribe China Zone - YouTube

linux - How to concat 2 mp4 videos by ffmpeg without having a messing result? - Super User

Childhoods of exceptional people - by Henrik Karlsson

node.js - From multiple video files to single output - Stack Overflow

Ranked L/S - Turning a formula into a strategy

Warp: The terminal for the 21st century

Deep Double Descent

Understanding the Neural Tangent Kernel – Rajat's Blog – A blog about machine learning and math.

(5) Get with Him (Ron Carroll's Spirit Filled Mix) - YouTube

(5) LYRIC HOOD - LOSE MY MIND [M-PLANT] - YouTube

Liquid Dust - Father Stretch My Hands [Edit] by Full Crate & Jarreau Vandal present: Liquid Dust

How America Took Out The Nord Stream Pipeline

My 2022 self (I don't know them) was very wrong about meditation, huge monitors, and... sleep. - Alexey Guzey

(6) Harrison Bergeron Full Movie - 1995 Starring Sean Astin, Christopher Plummer - Award Winning - YouTube

[2107.03006] Structured Denoising Diffusion Models in Discrete State-Spaces

TileMaker

Pimsleur Premium Chinese (Mandarin) | Pimsleur All Access | Learn Chinese (Mandarin) App

Lost Angel (Pure) – SEKUTA SEVEN