A Practical Introduction to Large Language Models (LLMs)

This is the 1st video in a series on using large language models (LLMs) in practice. I introduce LLMs and three levels of working with them.

Music by Me

--

Intro - 0:00
What is an LLM? - 1:13
Zero-shot Learning - 3:36
How do LLMs work? - 5:44
3 Levels of Using LLMs - 7:52
Level 1: Prompt Engineering - 8:22
Level 2: Model Fine-tuning - 11:00
Level 3: Build your own - 13:13

[HaneNaghshbandi]

Finally I found a video explaining such a complex concept in a simple way. Thanks a lot. It was so good!

[barclayiversen]

This channel is going to become my new addiction

[DRAI-ownq]

Thanks Shaw! I always look forward to your videos

[ajalipio]

I love the clarity and simplicity of your videos. I'm a new fan and you got a new sub! 🥰

[IndyScriabin-dlot]

Excellent material you covered herein as an executive summary and TL; DR of LLMs. Thank you very much.

[enoack]

Very good high level explanations that make the subject(s) very accessible. Thanks!

[helrod]

I appreciate your simple explanation of a complex subject.

[emammadov]

this is amazing series of videos. Well done for explaining this to us in such an easy-to-understand way

[pmh_]

This was great, looking forward to future videos.

[hoangng]

It would be great if you could make a series about fine-tuning LLM/s for a specific area of tasks. The reasons are:
1) The number of people requiring their own LLM/s is very small; if they need their own models, they already have them.
2) I have seen many tutorials about fine-tuning, but they only touch the surface layer. Plus, preparing data in the form of questions and answers takes so much effort that it is not practical.

Thank you

[flimsandmediaproduction]

been struggling with the concept. your video indeed helped alot<3

[-minutemotivationu]

Become a fan of you, nice way of teaching cool, calm and to the point,

[hardcoder-yw]

@Shaw Talebi - Thanks for creating such amazing video. Indeed it helped so much. I got a question here, do you provide AI or LLM training? Perhaps, boot camp?

[upmjugg]

Thanks, I see very few applications other than cute stuff. Any large company maybe has a 500 word vocabulary. All other words come from a list of persons, places and things. A simple syntax language can be designed, implemented, and maintained far easier to produce the same structure of an action request and its qualifiers. So you build lists of lists (car parts, animals, countries, ...) take all these words out, and substitute a variable into the model. "what <us state names> are you <contacting types> from?". Then of course order is not important. Computer "forms" are great, since they provide "lists" of things to choose from and/or to browse. Many things are not obvious "wind" as moving air vs. "wind" as to turn handle. Accuracy is more important than speed. Set aside external inquiries, and look at a company's internal questions by employees who know the vernacular, then it makes more sense to work on a syntax language. The objective for any company it to eliminate meetings and keep the employee's butts in their own chairs, this our only job. We should not be going down another application that will be obsolete before it's finished. Creating another layer / monopoly will only take money out of everyone's pocket.

[anneest]

Thanks for sharing this, very good and condensed information (I got the link to your YT channel from your article in towardsdatascience).
Looking forward to seeing future videos with examples, cheers 👍

[ifycadeau]

Finally! Prompt engineering is so underrated!!🙌🏾

[arpitrawat]

Thanks for the video. Would love to hear about different use cases with implementation.

[lookup]

Very well explained video. Good Introduction

[yahya]

thank you very much for this well explained video !

[greatgatsby]

This was useful -even though I did not understand everything!