Sensitive content

This media may contain sensitive content.

Loading video...

Video Failed to Load

Go Home

Say what?! Another thread to kick off the Weekend?! ๐Ÿ˜ฑ How about performers who deserve your attention? ๐Ÿ‘€ Here we go: ๐Ÿ˜ค ๐“๐จ๐ฉ ๐Ÿ๐ŸŽ ๐๐ž๐ซ๐Ÿ๐จ๐ซ๐ฆ๐ž๐ซ๐ฌ ๐˜๐จ๐ฎ ๐’๐ก๐จ๐ฎ๐ฅ๐ ๐๐ž ๐–๐š๐ญ๐œ๐ก๐ข๐ง๐  ๐‘๐ข๐ ๐ก๐ญ ๐๐จ๐ฐ ๐Ÿ˜ค (In my opinion) NUMBER 10: Stella Luxx

103,298 views โ€ข 2 months ago โ€ขvia X (Twitter)

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

THIS ANSWER. โ€œsaying you wonโ€™t be the favorites in vegas. i saw you do this at least another two times: โ€˜we are not the favorites.โ€™ do you think a change of mindset is needed?โ€ lando: โ€œno, i can say what i want, i can think what i want, i tell you what i always am, i always try and be as honest as i can be. if i don't think we're going to be quick, i don't think we're going to be quick. and i'm not saying i'm going to be 10th, i'm just saying i think it's going to be difficult to win. we were a long way off, just go and look at the data from last year, look at the racetrace, we were miles off. and there's been plenty of races where we've not been quick enough this year, so it's not like we've won every single race and you're expecting me to say those things. i'm just giving my opinion on โ€˜do i think it's going to be as easy?โ€™ i won last weekend by 30 seconds, very, very easy. i won today by pushing a lot more, only 10 seconds, and max was probably the quickest out on track today. do i think that at a track that we've never been good at, we were very good here two years ago, we almost challenged max for the win, we've never been good in vegas. so why am i going to think, โ€˜yeah, it's going to be fine, whatever?โ€™ i'm giving my opinion, i'm giving my honest opinion on how i think we're going to be. we've never been good there, so i'm not the most confident about going into this race. maybe i'll win, then we'll see. but i'm not going to lie and say โ€˜yeah, i'm very confident and i think it's going to be an easy weekendโ€™ because i don't think that's how it's going to be. so no, i mean, you're very right to have your own opinion on what you think i should say and what i should not say and whatever, but i'll do what i like.โ€

ray

756,816 views โ€ข 9 months ago

New short course: Attention in Transformers: Concepts and Code in PyTorch. Last week we released a course on how LLM transformers work. This week, go deeper and learn about the technical ideas behind the attention mechanism, and see how to code it in PyTorch. This course is built with Joshua Starmer, Founder and CEO of StatQuest. The attention mechanism was a breakthrough that led to transformers, the architecture powering large language models like ChatGPT. Transformers, introduced in the 2017 paper: "Attention is All You Need" by Viswani and others, took off because of its highly scalable design. In this course, youโ€™ll learn how the attention mechanism, a key element of transformer-based LLMs, works and implement it in PyTorch. You'll develop deep intuition about building reliable, functional, and scalable AI applications. What you will do: - Understand the evolution of the attention mechanism, a key breakthrough that led to transformers. - Learn the relationships between word embeddings, positional embeddings, and attention. - Learn about the Query, Key, and Value matrices, and how to produce and use them in attention. - Walk through the math required to calculate self-attention and masked self-attention to learn why and how they work. - Understand the difference between self-attention and masked self-attention and how one is used in the encoder to build context-aware embeddings and the other is used in the decoder for generative outputs. - Learn the details of the encoder-decoder architecture, cross-attention, and multi-head attention and how they are all incorporated into a transformer. - Use PyTorch to code a class that implements self-attention, masked self-attention, and multi-head attention. There're lots of exciting technical details in this course. Please sign up here:

Andrew Ng

132,400 views โ€ข 1 year ago