How Large Language Models Work 

I don't know what is more impressive, LLMs or this guy's ability to write backwards perfectly.

Very nice explanation, short and to the point without getting bogged down in detail that is often misunderstood. I will share this with others

Nicely done! You explain everything very clearly. This video is concise and informative. I will share with others as an excellent foundational resource for understanding LLMs.

Great video presentation! Martin Keen delivers a superbly layman friendly elucidation of what are otherwise very 'high tech talk' to people like me who do not come from a tech based professional background. These types of content are highly appreciable, and in fact motivate further learning on these subjects. Thank you IBM, Mr. Keen & team. Cheers to you all from Sri Lanka.

Martin keen as awesome as usual...... so natural. I love his talks and somehow I owe to him my understandingof complicated subjects in AI> thanks......

Really really enjoyed this primer. Thank you and great voice and enthusiasm!

Hey, nice job!!! yeah, I'd like to see more of these kinds of subjects in the present and the future as well!!!

great presentation, feels like personal asistant, great!

Very elaborate explanation. Thank you

tbh, I just love his voice and ready to listen all his videos 🤗

perfect for learning LLMs

IBM big thanks to you for all this videos! This videos are really helpfull

Very nicely done.

I've liked and subscribed and done it again a thousand times in my mind

Thank you for posting this video. What are the other architectures available apart from Transformer?

Greate explanation ❤

Can a subsequent SFT and RTHF with different, additional or lesser contents change the character, improve, or degrade a GPT model?

Large language models like GPT-3 work by using deep learning techniques, specifically a type of neural network called a transformer. Here's an overview of how they work: 1. **Data Collection**: Large language models are trained on vast amounts of text data from the internet, books, articles, and other sources. This data is used to teach the model about language patterns, grammar, syntax, semantics, and context. 2. **Tokenization**: The text data is tokenized, which means breaking it down into smaller units such as words, subwords, or characters. Each token is assigned a numerical representation. 3. **Training**: The model is trained using a process called supervised learning. During training, the model learns to predict the next word or token in a sequence based on the preceding context. It adjusts its internal parameters (weights and biases) through backpropagation to minimize prediction errors. 4. **Transformer Architecture**: Large language models like GPT-3 use a transformer architecture, which is highly effective for handling sequential data like language. Transformers include attention mechanisms that allow the model to focus on relevant parts of the input sequence while generating output. 5. **Fine-Tuning**: After pre-training on a large dataset, language models can be fine-tuned on specific tasks or domains. This process involves additional training on a smaller dataset related to the target task, which helps the model specialize in that area. 6. **Inference**: Once trained, the language model can generate text by predicting the most likely next tokens given an input prompt. It uses the learned patterns and context from training to generate coherent and contextually relevant responses. 7. **Continual Learning**: Some language models support continual learning, which means they can be updated with new data over time to improve their performance and adapt to changing language patterns. Overall, large language models combine sophisticated neural network architectures, extensive training data, and advanced training techniques to understand and generate human-like text.

such a great video

Very nice explanation, are these foundation models are proprietary? How many foundation models exist?

Intro to LLM’s. Thanks

Interesting explanation

Lol. I only knew Martin Keen from Brulosophy. This is sort of mindblowing.

What is meant by, when referring to "sequences of words", "understanding"? I mean, what does "understanding" mean in that context?

Thank You Sir ❤

Imagine a world where wikipedia no longer needs human contributors. You just upload the source material, and an algorithm writes the articles and all sub-pages, listing everything it knows about a certain fictional character because it read the entire book series in half a second. Imagine having a conversation with the world's most eminent Star Wars expert.

I get a remote job offer. The duty is AI training for LLM. Shall i go for it? What do you think?

Hi Martin, are you there around? Could you please talk about " Emerging LLM App Stack" ? Thanks in advance!

Knowig about LLM Model Work Mr. Martin Keen. Can you larger focus on LLM Modelling and what exact related stuff(program skills) is requried. Thank you so much it was pleasant video i appreciated.

The term large can not be referred to as large data; to be precise it is the number of parameters that is large. So slight correction.

Thanks dude

That's amazing! Our company has a great project that can benefit from this and then use the proceeds to benefit mankind. How can we speak more about this? I am very intrigued.

Amazing!

Thanks . How much to build the own LLM

Nice explanation! But I am still missing the most important point. How does one control relevance of the produced results? E.g. ChatGPT can answer questions. So far, what you explained is a model that can predict -> generate the next word in a document, given what has already been written. However, given a set of existing sentences, there is a multitude of ways to produce the next sentence, that would be somewhat consistent with the rest of the document. How does one go from plausible text generators to desired text generators?

What is quantized version of models, how it would be created?

Other than the physical limitation of space like any other computer has, it seems to me that technology like this should be applicable to robotics and allow for creation of much smarter and adaptive robotics projects and creations.

In this presentation, there was not enough detail on Foundation Models as a baseline to then explain what LLMs are.

Does anyone know what program he uses to sketch on screen like that?

Wait a minute. Did he really write in mirror handwriting?

so the transformers only for the language and text related things??

Lucid, thanks

1 PB = 1024 TB 1TB = 1024 GB 1GB = 1024 MB 1MB = 1024 KB 1KB = 1024 B 1B = 8 bits So 1 PB = 1024 * 1024 * 1024 * 1024 *1024 Bytes Multiply it again by 8 to get the number of bits. Guys do correct me if I'm wrong!!

How did you learn to write backwards

What's the difference between large language models and text to speech

Thank you for explaining! 🪲 Min. 3:37 is the major "bug" 🐞 within the learning system, *it does not start off with a related guess, it's random.* 🌬 I can't wait until the *brain slice chips* can last longer and get trained like a real human brain that is actually learning by feelings and repeating instead of random guessing and then correcting itself until the answer is appropriate. They could soon replace A.I. technology completely, so maybe we shouldn't hype too much about it. After all the effort, energy and money we put into A.I. and new technology, it's no doubt that *we could have educated our children better* instead of creating a fake new world, based on pseudo knowledge extracted from the web. 👨‍👩‍👧‍👦👨‍👩‍👧‍👧 Nobody want's to be r3placed without having the benefit of the machine. General taxes on machines and automated digital services could fund better education for humans. Dear A.I.: You know what is real fun? Planting a tree in real life! 🍒

Did you only mirror the screen and it looks like you can write RTL, isnt it?! wow

Something tells me “The sky is the limit” here 👀

@2:15 a different sequence. this is just for fun .

could haver been better, most of it was speculative when it came to application building, not to mention the laws governing it

Need one use case

How are you able to write that way

NİCE VİD O7

How does ChatGPT know about itself and its own behavior? If you ask questions about those topics, it will answer intelligently and accurately about itself and its own behavior. It will not just spout random from patterns from the internet. How does it know this?

but how its possible to an LLM innovate when its being trained with over human knowledge boundaries?

Is this video mirrored?

So LLM based AI is just language not ‘intelligence’? Based on what it’s read it knows or guesses what usually comes next? So zero intelligence?

How does this presentation work? You do are not mirror writing behind a glass pane, do you?

I don’t even know where to begin. 😵‍💫

Still dont get it

Getting hallucinations!

How many 'parameters' does the human brain have, I wonder.

Ugh corporate videos..... the horror

Why does a gigabyte have more words then a petabyte? I am lost already!!! 1 Gig =178 million words, 1 petabyte is 1.8x10^14 words, and there are only 750,000 words in the dictionary?

What to do if a Large Language Model after putting all petabytes of data into it is still talking nonsense?

$PLTR

How is he writing backwards

You could have finished the video by saying an LLM like Chat GPT could have produced the entire explanation for this video.. (I think u hinted the same)

Hire someone next time who can explain it to the average John and Jane. Talk about 7 billion parameters and you already have John and Jane scrathing their head like crazy what the fuck he's talking about. Oh, yeah, some in the comment section understand it... but they're not the average John and Jane... they're often familiar with coding, data, business processes, computers, etc

This is scarrry

Isn't it using the most likely thing that humans defined and just uses patterns of what's most expected based on how humans interact and info put in..... that's not complicated. How do they not understand how it works....

If IBM knows that, why they didnt implement it in the Watson that were useless 😂😂😂

Not a very good video. Really didn't explain much. You could have said so much more in 5:33 than slowly drawing things and talking about business applications.

1 petabyte is not 1m gigabytes, it is 1,000 gigabytes. I thought this speech is coming from an engineer but perhaps it is just a hired actor.

Explaining the constituent parts, the end product, is not the same as explaining how something works. Bad video.