This was one of the best explanation videos I have ever seen! Well structured and right complexity grade to follow without getting a headache. 👌
@muhannadobeidat8 ай бұрын
Excellent video. Well spoken. Nice visualizations.
@420_gunna10 ай бұрын
This felt very nicely taught -- I loved that you pulled back a summary/review at the end of the video - great practice. Please continue, thank you!
@vineetkumarmishra29899 ай бұрын
wonderfully explained !! Thanks for the video.
@carlpeterson82795 ай бұрын
Great summary/outline at 17:16 This video covers a lot of relevant topics for neural networks and edge AI.
@jokmenen_9 ай бұрын
Awesome video!
@heteromodal11 ай бұрын
What a great video! Thank you!
@huiwencheng458511 ай бұрын
Fantastic introduction and explanation !
@bonob01236 ай бұрын
that was really nicely done. as a non-expert, I feel like I can now have a great general idea of what a quantized model is. thank you
@ljkeller_yt8 ай бұрын
Great format, succinctness, and diagrams. Thank you!
@RamBabuB-r9s Жыл бұрын
your teaches so excellent.. we accepted many more videos from your side to understand for the fundamental NLP
@kevon217 Жыл бұрын
^
@unclecode10 ай бұрын
Great content, well done. Please make a video for ONNX, and another one for Flash Attention. Appreciate.
@kevon217 Жыл бұрын
Thanks for this!
@xuantungnguyen97193 ай бұрын
You are a good teacher
@AmishaHSomaiya7 ай бұрын
Great summary, thank you.
@jeremyuzan11698 ай бұрын
Great video
@xiaoxiandong73822 ай бұрын
super clear
@MuhammadAli-dw7mv7 ай бұрын
nicely done
@tosinadekunle6463 ай бұрын
Thank you for the video Sir. So please, is quantization just about feature engineering task of data types enforcement of enforcing data types that take only small space? Or it is more than that?
@EfficientNLP3 ай бұрын
I'm not sure if this is what you're asking, but model quantization is not related to feature engineering or enforcing data types; it is methods for making a model more space or compute-efficient after training.
@tosinadekunle6463 ай бұрын
@EfficientNLP But looking at what you have shown in the examples there, it says changing data types to for example int8 for both the input features and the weights. Which i think can be done in a line of code like model.weight.torch.int8. Looking at that, it looks like we must try to ensure that the dataset is stored using a data type that utilizes less memory and to ensure that this is done before model training. What do you think sir?
@DurgaNagababuMolleti6 ай бұрын
Superb
@hrsight8 ай бұрын
nice video
@yunlu465711 ай бұрын
Excellent video, learnt a lot! However, the definition of zero-point quantization is off. What you're showing in the video is the abs-max quantization instead.
@EfficientNLP11 ай бұрын
The example I showed is zero-point quantization because 0 in the original domain is mapped to 0 in the quantized domain (before transforming to unsigned). In abs-max (not covered in this video), the maximum in the original domain would be mapped to 127, and the minimum would be mapped to -128.
@ricardokullock25357 ай бұрын
And if one was to quantize a distilled model? Is the outcome any good?
@EfficientNLP7 ай бұрын
Yes, these two techniques are often used together to improve efficiency.
@julians778516 күн бұрын
I heard multiply by 0 operations are faster to process. Are you sure all operations take the same speed?
@EfficientNLP16 күн бұрын
Generally, for most instructions and most hardware, arithmetic takes a fixed amount of time per operation and does not get faster if the inputs are zeros. However, multiplying by 0 could be faster if the software logic checks for zeros to skip some operations, like in sparsity-aware methods.
@julians778516 күн бұрын
@@EfficientNLP Thanks for the reply!
@nothingtoseehere576020 сағат бұрын
I am extremely grateful for this detailed explanation, but I am left with a lot of questions. Can I pm you?
@EfficientNLP16 сағат бұрын
Sure, happy to discuss over LinkedIn!
@andrea-mj9ce9 ай бұрын
The explanation for distillation remains at the surface, it is not enough to understand it
@EfficientNLP9 ай бұрын
If you have any specific questions I’ll try to answer them!