Thanks for the video! Very informative! Just to check: At @1:03:42, 3. be "... save back the result to HBM."?

Dear Sir please make a video on details explanation on code of diffusion model . It will be helpful. Thanks for understanding and valuable video

Always a fan of your video. Your explanation is very informative and helpful for beginner data scientist. Thank you very much.

Great content ,deep understanding after watching video

Please use bigger font size. Its difficult to read

i literally fell asleep, where did this come from.

Best explanation I found on KZbin, thank you!

Amazing video.

life saver 😭 thank you so very much lots of love and gratitude 💙💙

awesome video man!

superb explanation please make a vedio on RNN in depth with math as well.

Amazing !! I finally understood everything. Good Job, all your videos have in-depth understanding

39:25 Renormalization will not bring the values to the range of [0,1]. Take for example the samples: (-2, 0, 0, 0, 0, 0, 0, 0, 2) But would rather squeeze (or unsqueeze) the values depending on their range. As a matter of fact, a sample with variance 1 and mean 0 will surely have at least one value outside of the range [-1,1]. In any case, amazing videos, thank you.

yes , this is what i wanted

Best explanations of splines i have seen. Legit 100%

PLEASE explain spacetimeformer

Great 👍

hello sir can you please make a tutorial on pytorch to fellow along with your pytorch projects. Thank you in advance

One of the best videos for BERT in youtube

Thank you for the amazing explanation

Both VAE and AE map the input over a latent space, the difference lies on the **structure** of this latent space. The AE latent space is not "well-organized" as well as the VAE's latent space.

Hello, thanks to your great vedio!! There are some puzzle confusing me a lot. I am wondering how to train Diffusion Model with cfg. I think according to input, the targets also have two images. So, the target image for condiftional input is what? And, the target image for non-conditional input is what? 😀😀😀

amazing work, thank you so much !

was immersing myself in the video. all of a sudden, Umar spoke to his cat in Chinese...haha... now I understand why some comments are left in Chinese..

can someone please help me how to run this to produce the images from text. I have placed all the files like the GitHub repository still when i run the demo.ipynb file its gives me this error TypeError: 'weights_only' is an invalid keyword argument for Unpickler()

can you please share your slides of this as well as for attention is all you need paper in .pptx( power point format )

Umar, you are a great teacher. I have not seen such a great explanation of transformer. Your transformer from scratch coding is also awesome. So, basically you understand which part needs more explanation. Thanks for your effort.

can you make tutorial video on model like Perplexity that use website live search

can you make tutorial video on model like Perplexity that use website live search

Hello Umar, you always produce the most concise and clear content ever! I was wondering if you are planning to do any video on the stable diffusion 3 since the paper is out? It would be really great if you could help explain how the flow matching helps or changes regular diffusion models! Thank you again for your content and work. 非常感谢！

Thanks!

Amazing content, thanks! I'm very excited about the continual learning properties of these networks.

Please do a video where you show the process from scratch so we can do this with voice models ✊🏼

Good video, quality content.

I learnt a lot from following the steps out of this video and create a transformer myself step by step!! Thank you!!

Awesome explanation. Cls token is important just because there is no zero values with others token?

sir, your explanation is just beyond awesome!!! Thank you so much for creating such content. Sir I didn't get the residual connections part. As I am from India, I was working on Indic Languages, so i had to make more code but that's just okay. I just want if you could please help in understanding beam search code, the one which you also gave in the GitHub File. Also, if you could give the code for evaluating the BLEU Score. I'll be really grateful to you. And again, thank you so much for such a comprehensive content. We'd love to see your more videos especially in Generative AI! P.S. : I didn't understand how you wrote it, what I've understood is that we have to take the input of the previous layer and then add with o/p of the same layer and then apply layer norm on that. Basically Add and then LayerNorm. Please help me correct mysefl!

Sei troppo forte, spieghi bene ed è facile seguirti. Vai avanti così!

This is just awesome!

Hi, I just happen to see your video. It's really amazing, your channel is so good with valuable information. Hope, you keep this up because I really love your contents.

Very clear, well explained, top notch!

best video I have ever seen on whole youtube eon transformer model. Thank you so much sir!

the constant you scale by the x come from averaging over a bunch of examples generated by the vae, in order to ensure they have unit variance with the variance taken over all dimensions simultaneously, scale_factor = 1 / std(z)

i came here form your VAE video. after that, should i be doing the 5hr long stable diffusion or this one?? what do you suggest?

Great video! I'm wondering, is there any reason to save the positional encoding vector? I don't see why you would need to save it since it seems to always be the same value considering the init parameters don't change.

Great explanation. Clean!!! Reminds me of school where our physics teacher taught everything practical and it felt so simple. subs+1👍

Good vid boss

23:39 -> loved that intuitive explanation!

Brilliant video! Really clear and with just the right amount of details!

Thank you for this video!