The Attention Mechanism in Large Language Models

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

[@arvindkumarsoundarrajan9479]

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🎉

[@user-bw5np7zz5m]

I love your clear, non-intimidating, and visual teaching style.

[@SerranoAcademy]

Thank you so much for your kind words and your kind contribution! It’s really appreciated!

[@RG-ik5kw]

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!

[@malikkissoum730]

Best teacher on the internet, thank you for your amazing work and the time you took to put those videos together

[@gunjanmimo]

This is one of the best videos on KZbin to understand ATTENTION. Thank you for creating such outstanding content. I am waiting for upcoming videos of this series. Thank you ❤

[@EricMutta]

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!

[@nealdavar939]

The way you break down these concepts is insane. Thank you

[@calum.macleod]

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.

[@TheMircus224]

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!

[@pruthvipatel8720]

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.

[@JyuSub]

Just THANK YOU. This is by far the best video on the attention mechanism for people that learn visually

[@aadeshingle7593]

One of the best intuitions for understanding multi-head attention. Thanks a lot!❣

[@apah]

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

[@bobae1357]

best description ever! easy to understand. I've been suffered to understanding attention. Finally I can tell I know it!

[@mohandesai]

One of the best explainations of attention I have seen without getting lost in the forest of computations. Looking forward to future videoas

[@SerranoAcademy]

Thank you so much!

[@mohameddjilani4109]

I really enjoyed how you give a clear explanation of the operations and the representations used in attention

[@ajnbin]

Fantastic !!! The explanation itself is a piece of art. The step by step approach, the abstractions, ... Kudos!! Please more of these

[@saeed577]

THE best explanation of this concept. That was genuinely amazing.

[@sayamkumar7276]

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

[@drdr3496]

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.

[@dr.mikeybee]

Nicely done! This gives a great explanation of the function and value of the projection matrices.

[@amoghjain]

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!!

[@kevon217]

Wow, clearest example yet. Thanks for making this!

[@hyyue7549]

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.

[@anipacify1163]

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

[@arulbalasubramanian9474]

Great explanation. After watching a handful of videos this one really makes it real easy to understand.

[@karlbooklover]

best explanation of embeddings I've seen, thank you!

[@soumen_das]

Hey Louis, you are AMAZING! Your explanations are incredible.

[@ccgarciab]

This is such a good, clear and concise video. Great job!

[@abu-yousuf]

amazing explanation Luis. Can't thank you enough for your amazing work. You have a special gift to explain things. Thanks.

[@JorgeMartinez-xb2ks]

El mejor video que he visto sobre la materia. Muchísimas gracias por este gran trabajo.

[@docodemo727]

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!

[@dragolov]

Deep respect, Luis Serrano! Thank you so much!

[@RamiroMoyano]

This is amazingly clear! Thank for your your work!

[@pranayroy]

Kudos to your efforts in clear explanation!

[@justthefactsplease]

What a great explanation on this topic! Great job!

[@VenkataraoKunchangi-uy4tg]

Thanks for sharing. Your videos are helping me in my job. Thank you.

[@MikeTon]

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!

[@kafaayari]

Well the gravity example is how I understood this after a long time. you are true legend.

[@orcunkoraliseri9214]

Wooow. Such a good explanation for embedding. Thanks 🎉

[@alijohnnaqvi6383]

What a great video man!!! Thanks for making such videos.

[@prashant5611]

Amazing! Loved it! Thanks a lot Serrano!

[@orcunkoraliseri9214]

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 😊

[@sari54754]

The most easy to understand video for the subject I've seen.

[@bananamaker4877]

Explained very well. Thank you so much.

[@eddydewaegeneer9514]

Great video and very intuitive explenation of attention mechanism

[@hkwong74531]

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. 👍🏻👍🏻👍🏻👍🏻

[@agbeliemmanuel6023]

Wooow thanks so much. You are a treasure to the world. Amazing teacher of our time.

[@user-dg2gt2yq3c]

It's so great, I finally understand these qkvs, it bothers me so long. Thank you so much !!!

[@debarttasharan]

Incredible explanation. Thank you so much!!!

[@caryjason4171]

This video helps to explain the concept in a simple way.

[@perpetuallearner8257]

You're my fav teacher. Thank you Luis 😊

[@tvinay8758]

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

[@aaalexlit]

That's an awesome explanation! Thanks!

[@erickdamasceno]

Great explanation. Thank you very much for sharing this.

[@notprof]

Thank you so much for making these videos!

[@ignacioruiz3732]

Outstanding video. Amazing to gain intuition.

[@satvikparamkusham7454]

This is the most amazing video on "Attention is all you need"

[@davutumut1469]

amazing, love your channel. It's certainly underrated.

[@LuisOtte-pk4wd]

Luis Serrano you have a gift for explain! Thank you for sharing!

[@jeffpatrick787]

This was great - really well done!

[@DeepakSharma-xg5nu]

I did not even realize this video is 21 minutes long. Great explanation.

[@vishnusharma_7]

You are great at teaching Mr. Luis

[@cyberpunkdarren]

Very impressed with this channel and presenter

[@bankawat1]

Thanks for the amazing videos! I am eagrly waiting for the third video. If possible please do explain the bit how the K,Q,V matrices are used on the decoder side. That would be great help.

[@WhatsAI]

Amazing explanation Luis! As always...

[@SerranoAcademy]

Merci Louis! :)

[@bengoshi4]

Yeah!!!! Looking forward to the second one!! 👍🏻😎

[@jayanthkothapalli9.2]

Wow wow wow! I enjoyed the video. Great teaching sir❤❤

[@epistemophilicmetalhead9454]

Word embeddings Vectorial representation of a word. The values in a word embedding describe various features of the words. Similar words' embeddings have a higher cosine similarity value. Attention The same word may mean different things in different contexts. How similar the word is to other words in that sentence will give you an idea as to what it really means. You start with an initial set of embeddings and take into account different words from the sentence and come up with new embeddings (trainable parameters) that better describe the word contextually. Similar/dissimilar words gravitate towards/away from each other as their updated embeddings show. Multi-head attention Take multiple possible transformations to potentially apply to the current embeddings and train a neural network to choose the best embeddings (contributions are scaled by how good the embeddings are)

[@drintro]

Excellent description.

[@maysammansor]

you are a great teacher. Thank you

[@SulkyRain]

Amazing explanation 🎉

[@thelookerful]

This is wonderful !!

[@user-uq7kc2eb1i]

This video is really clear!

[@traveldiaries347]

Very well explained ❤

[@surajprasad8741]

Thanks a lot Sir, clearly understood.

[@khameelmustapha]

Brilliant explanation.

[@naimsassine]

super good job guys!

[@sukhpreetlotey1172]

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

[@SerranoAcademy]

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. :)

[@EigenA]

Great video!

[@divikchoudhary8873]

This is just Gold!!!!!

[@serkansunel]

Excellent job

[@ProgrammerRajaa]

Your videos are so awesome plse upload more video thanks a lot

[@muhammadsaqlain3720]

Thanks my friend.

[@shashankshekharsingh9336]

thank you sir 🙏, love from india💌

My comment is just an array of letters for our algorithmic gods..Good stuff.

[@waelmashal7594]

Great video

[@deeplearningwithjay]

You are amazing !

[@mostinho7]

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

[@bravulo]

Thanks. I saw also your "Math behind" video, but still missing the third in the series.

[@SerranoAcademy]

Thanks! The third video is out now! kzbin.info/www/bejne/p5K6foKPm5mln5o

[@ernesttan8090]

wonderful!

[@benhargreaves5556]

Unless I'm mistaken, I think the linear transformations in this video incorrectly show the 2D axis as well as the object changing position, but in fact the 2D axis would stay exactly the same but with the 2D object rotating around it for example.

[@TemporaryForstudy]

oh my god never understood V,K,Q as matrix transformations, thanks luis, love from india

[@preetijani9658]

Amazing

[@today-radio-in-the-zone]

Thanks for your great effort to make people understand it. I, however, would like ask one thing such that you have explained V is the scores. scores of what? My opninion is that the V is the key vector so that the V makes QKT matrix to vector space again. Please make it clear for better understanding. Thanks!

[@samirelzein1095]

The great Luis!

[@liminal6823]

Fantastic.

[@angminhquan1491]

love the video

[@SergeyGrebenkin]

At last someone explained the meaning of Q, K and V. I read original article and it just says "Ok, let's have 3 additional matrix Q, K and V to transform input embedding" ... What for? Thanks for explanation, this video really helps!

[@tristanwheeler2300]

Thanks so much for making this video. It's difficult to find people explaining these concepts on a higher level. One thing I missed was how we are able to have two different apples in the matrix. If something like this is possible then I'm guessing we have several instances every single word floating around - the ones with several different contextual potentials very scattered in the matrix, while the ones without so much variation in meaning closer together. So is this process where the positions of the words in the matrix is reevaluated based on the "gravitational pull" from the associations of the other words in the sentence also a process deciding whether or not to continue to use an existing instance of the word or to create an entirely new version of the word in a new position in the matrix?