The Attention Mechanism in Large Language Models
Вставка
- Опубліковано 3 січ 2025
- Attention mechanisms are crucial to the huge boom LLMs have recently had.
In this video you'll see a friendly pictorial explanation of how attention mechanisms work in Large Language Models.
This is the first of a series of three videos on Transformer models.
Video 1: The attention mechanism in high level (this one)
Video 2: The attention mechanism with math: • The math behind Attent...
Video 3: Transformer models • What are Transformer M...
Learn more in LLM University! llm.university
I have been reading the "attention is all you need" paper for like 2 years. Never understood it properly like this ever before😮. I'm so happy now🎉
This is a great video (as are the other 2) but one thing that needs to be clarified is that the embeddings themselves do not change (by attention @10:49). The gravity pull analogy is appropriate but the visuals give the impression that embedding weights change. What changes is the context vector.
Your videos in the LLM uni are incredible. Builds up true understanding after watching tons of other material that was all a bit loose on the ends. Thank you!
I love your clear, non-intimidating, and visual teaching style.
Thank you so much for your kind words and your kind contribution! It’s really appreciated!
Best teacher on the internet, thank you for your amazing work and the time you took to put those videos together
This video is amazing!
Appreciate Luis for his skill of explaining PhD level concepts as easier that 9th grade student can understand.
I found this channel is a diamond mine for beginners.
Thanks Luis.
This is one of the best videos on UA-cam to understand ATTENTION. Thank you for creating such outstanding content. I am waiting for upcoming videos of this series. Thank you ❤
THE best explanation of this concept. That was genuinely amazing.
This channel is uderrated, your explainations is the best among other channels
best description ever! easy to understand. I've been suffered to understanding attention. Finally I can tell I know it!
Just THANK YOU. This is by far the best video on the attention mechanism for people that learn visually
Truly amazing video! The published papers never bother to explain things with this level of clarity and simplicity, which is a shame because if more people outside the field understood what is going on, we may have gotten something like ChatGPT about 10 years sooner! Thanks for taking the time to make this - the visual presentation with the little animations makes a HUGE difference!
This was hands down the best explanation I've seen of attention mechanisms and multi head attention --- the fact I'm able to use these words in this sentence means I understand it
The world needs people like Serrano more, who explain the shit out of ambiguities and lead us back to the age of wisdom.
absolutely loved the last part with explaining linear transformations of query key and values. thank you so much!
Omg this video is on a whole new level . This is prolly the best intuition behind the transformers and attention. Best way to understand. I went thro' a couple of videos online and finally found the best one . Thanks a lot ! Helped me understand the paper easily
I appreciate your videos, especially how you can apply a good perspective to understand the high level concepts, before getting too deep into the maths.
These videos where you explain the transformers are excellent. I have gone through a lot of material however, it is your videos that have allowed me to understand the intuition behind these models. Thank you very much!
That was awesome, Thank you.
You saved me a lot of time reading and watching none-sense videos and texts
.
I really enjoyed how you give a clear explanation of the operations and the representations used in attention
So glad to see you're still active Luis ! You and Statquest's Josh Stamer really are the backbone of more ml professionals than you can imagine
One of the best intuitions for understanding multi-head attention. Thanks a lot!❣
The way you break down these concepts is insane. Thank you
This is such a good, clear and concise video. Great job!
Thank you for making this video series for the sake of a learner and not to show off your own knowledge!! Great anecdotes and simple examples really helped me understand the key concepts!!
I always struggled with KQV in attention paper. Thanks a lot for this crystal clear explanation!
Eagerly looking forward to the next videos on this topic.
This is one of the clearest, simplest and the most intuitive explanations on attention mechanism.. Thanks for making such a tedious and challenging concept of attention relatively easy to understand 👏 Looking forward to the impending 2 videos of this series on attention
What a beautiful way of explaining "Attention Mechanism". Great job Serano
Fantastic !!! The explanation itself is a piece of art.
The step by step approach, the abstractions, ... Kudos!!
Please more of these
Great explanation. After watching a handful of videos this one really makes it real easy to understand.
this video is really teaching you the intuition. much better than the others I went through that just throw formula to you. thanks for the great job!
Thank you for your explanation! I've always wondered why the attention mechanism in Transformers produces more effective embeddings compared to Word2Vec, and your video clarified this well. Word2Vec generates static embeddings, meaning that a word always has the same representation, regardless of the context in which it appears. In contrast, Transformers create context-dependent embeddings, where the representation of a word is influenced by the words around it. This dynamic approach is what makes Transformer embeddings so powerful.
Thanks Luis, been following your contents for a while. This video about attention mechanism is very intuitive and easy to follow
Kudos to your efforts in clear explanation!
amazing explanation Luis. Can't thank you enough for your amazing work. You have a special gift to explain things. Thanks.
Thanks!
7:00 even with word embedding, words can be missing context and there’s no way to tell like the word apple. Are you taking about the company or the fruit?
Attention matches each word of the input with every other word, in order to transform it or pull it towards a different location in the embedding based on the context. So when the sentence is “buy apple and orange” the word orange will cause the word apple to have an embedding or vector representation that’s closer to the fruit
8:00
¡Gracias!
Muchisimas gracias por tu colaboración!!! Que amable!
Excellent video. Best explanation on the internet !
Wow, clearest example yet. Thanks for making this!
best explanation of embeddings I've seen, thank you!
El mejor video que he visto sobre la materia. Muchísimas gracias por este gran trabajo.
The most easy to understand video for the subject I've seen.
Hey Louis, you are AMAZING! Your explanations are incredible.
Wooow thanks so much. You are a treasure to the world. Amazing teacher of our time.
This clarifies EMBEDDED matrices :
- In particular the point on how a book isn't just a RANDOM array of words, Matrices are NOT a RANDOM array of numbers
- Visualization for the transform and shearing really drives home the V, Q, K aspect of the attention matrix that I have been STRUGGLING to internalize
Big, big thanks for putting together this explanation!
Thanks, the explaination is so intuitive. Finally understood the idea of attention.
Great explanation with the linear transformation matrices. Thanks!
This is amazingly clear! Thank for your your work!
Nicely done! This gives a great explanation of the function and value of the projection matrices.
If I understand correctly, the transformer is basically a RNN model which got intercepted by bunch of different attention layers. Attention layers redo the embeddings every time when there is a new word coming in, the new embeddings are calculated based on current context and new word, then the embeddings will be sent to the feed forward layer and behave like the classic RNN model.
Can anyone confirm this?
amazing, love your channel. It's certainly underrated.
Amazing video... Thanks sir for this pictorial representation and explaining this complex topic with such an easy way.
What a great explanation on this topic! Great job!
I subscribe your channel immediately after watching this video, the first video I watch from your channel but also the first making me understand why embedding needs to be multiheaded. 👍🏻👍🏻👍🏻👍🏻
Great video and very intuitive explenation of attention mechanism
It was the most useful video explaining attention mechanism. Thank you
You're my fav teacher. Thank you Luis 😊
This video helps to explain the concept in a simple way.
This is the most amazing video on "Attention is all you need"
What a great video man!!! Thanks for making such videos.
It's so great, I finally understand these qkvs, it bothers me so long. Thank you so much !!!
I've really enjoyed with that way of you described and demonstrated matrices as linear transformations. Thank you! Why, because I like Linear Algebra 😄
Outstanding, thank you for this pearl of knowledge!
Very impressed with this channel and presenter
Well the gravity example is how I understood this after a long time. you are true legend.
Explained very well. Thank you so much.
I did not even realize this video is 21 minutes long. Great explanation.
Amazing! Loved it! Thanks a lot Serrano!
Deep respect, Luis Serrano! Thank you so much!
Thank you so much for the attention to the topic!
Thanks! Lol, I see what you did there! :D
I watched a lot about attentions. You are the best. Thank you thank you. I am also learning how to explain of a subject from you 😊
Thanks for sharing. Your videos are helping me in my job. Thank you.
This is amazing explanation! Thank you so much 🎉
Luis Serrano you have a gift for explain! Thank you for sharing!
Outstanding video. Amazing to gain intuition.
Amazing explanation Luis! As always...
Merci Louis! :)
Great explanation. Thank you very much for sharing this.
Excellent explanation. Thank you very much.
Superb explanation❤ please make more videos like this
Valeu!
@DiegoSilva-dv9uf Thank you so much for your kind contribution Diego!
Amazing explanation 🎉
This is an great explanation of attention mechanism . I have enjoyed your maths for machine learning on coursera. Thank you for creating such wonderful videos
Incredible explanation. Thank you so much!!!
You are great at teaching Mr. Luis
Wooow. Such a good explanation for embedding. Thanks 🎉
Wow wow wow! I enjoyed the video. Great teaching sir❤❤
First of all thank you for making these great walkthroughs of the architecture. I would really like to support your effort on this channel. let me know how I can do that. thanks
Thank you so much, I really appreciate that! Soon I'll be implementing subscriptions, so you can subscribe to the channel and contribute (also get some perks). Please stay tuned, I'll publish it here and also on social media. :)
I didn't get it on why do we add linear transformation like earlier too we had embeddings in other planes then why do shear transformation ? Please someone answer
Thank you for this amazing explanation
0:55 I thought Attention mechanisms had been around for a while before this paper, e.g. Bahdanu et Al (2014) and likely even earlier than that in some form, and this paper really served as i) an illustration that attention was...well, all you needed and ii) the introduction of the Transformer model architecture?
This video is really clear!
This was great - really well done!
That's an awesome explanation! Thanks!
you are a great teacher. Thank you
Amazing video, thank you very much for sharing!
Yeah!!!! Looking forward to the second one!! 👍🏻😎
Thank you so much for making these videos!
Paraphrase: we weigh each embedding by its score, and then add up all these weighted embeddings to obtain a really good embedding. Question to think about: why not just take the best embedding? Is it because averaging improves robustness to noise?
That is a great question! Yes, one thing is because of robustness. Also, each embedding may capture different things, one could be good for a certain topic (say, fruits) but terrible at others (say, technology).
Another reason is because of continuity. Let's say that you have embedding A, which has the highest score. The moment embedding B gets a higher score, you would switch abruptly from A to B, which creates a jump discontinuity. If you take the average, instead, you would smoothly go from, say 0.51*A + 0.49*B, into 0.49^A + 0.51*B, which is very similar.
Thanks for the answer, and for the wonderful video.
Maybe the next video will clarify how the weighting is achieved. At first I thought the V matrix provides the weighting of the different embeddings, but now I am not sure.
@@tantzer6113 yes! I thought the exact same thing, but then someone showed me they it doesn’t, those weights are recorded inside the transformer. I’m seeing that the V matrix is another embedding in which the transformation is made (and the K and Q are used to find the distances). But I’ll clarify this more in the next video.
Thanks. I saw also your "Math behind" video, but still missing the third in the series.
Thanks! The third video is out now! ua-cam.com/video/qaWMOYf4ri8/v-deo.html