A Guide to Building AI

Applications Using Large

Language Models (LLMs)
for Leaders
A Guide to Building AI
Applications LLMs for Leaders
• The discussion over Generative AI exploded last year after
the massively viral growth of ChatGPT.
• Along with that, a number of new terms entered the regular
parlance in the technology world - LLMs, Transformers,
Mistral, Hugging Face, RAG, Knowledge Graph, Stable
Diffusion, Vectors, LoRA, PEFT, so on and so forth.

• massively = kitlesel • Discussion = tartışma

• explode = patlamak, birden…-meye başlamak • Regular = yaygın
• Term = terim
• So forth = ve bunu gibi, gibi şeyler
• Parlance = deyim
 • In fact, if one made a list of jargons that emerged in the last one
year, it would possibly be more than what we have witnessed
over a decade or more in the world of technology.
• It also came with a question (thanks to Blockchain, Crypto and its
associated scams): ‘is this another passing fad, or something
real?’
• Now, the reports are in. Over 70% of business executives surveyed
by Gartner reported a top-down push for generative AI
implementation.
• Another McKinsey survey showed that 75% of participants
anticipated generative AI to significantly impact their industries
• within three years.
Emerge = ortaya çıkmak • Push = baskı
• Witness = tanık olmak, şahit olmak • Participant = katılımcı
• Decade = 10 yıl • Scam = dolandırıcılık
• Passing = geçici • Anticipate =beklemek, ummak
• Fad = heves, geçici bir moda
• Executive = yönetici
• Survey = anket yapmak, araştırmak
What Are Large Language
Models?
• Large Language Models (LLMs) are AI models that excel at
processing and generating text (or code, as we will see
later).
• Technically, they are deep learning models built using an AI
architecture that became popular after the 2017 paper:
‘Attention Is All You Need’. This architecture is known as the
Transformer architecture.
• So what are Transformers, then? Transformers are a specific
kind of neural network adept at handling sequential data,
like text.
• Excel = mükemmel • Handling = ele almak, işlemek
• Attention = dikkat • Kind = tür
• Architecture = mimari
• Transformer = dönüştürücü
• Adept = becerikli
 • This neural network model relies solely on an attention mechanism, a
technique that focuses on important parts of data (like key words in a
sentence).
• This approach is unlike the previous models which used recurrent neural
networks or convolutions.
• This focus on attention allows Transformers to process sequential data, such as
text, more effectively.
• Researchers found that not only are Transformers better at machine translation
tasks where sequential data is at play, they are also faster to train.
• By the way, this paper took the AI world by storm, and it is a must read for
anyone looking to understand the shift in the approach that the AI community
has taken towards building AI models.
• Rely = dayanmak • At play = söz konusu
• Solely = yalnızca • Allow = mümkün kılmak
• Attention = dikkat • Paper = makale
• Convolution = evrişim • Shift = değişim
• Sequential = sıralı • Looking to do sth = birşeyi yapmayı istemek
• Effectively = etkili bir şekilde
• Recurrent = tekrarlayan
Large Language Models Are Built
through Training. But Why?
• So, LLMs are built on the Transformer architecture and they
are trained on massive amounts of text data.
• However, simply putting together a neural network won’t
make it an LLM.
• It needs to be trained for it to actually work.
• The training process is a multi-stage process that involves
feeding the model massive amounts of text data and fine-
tuning its abilities.

• Massive = çok büyük • Feed = beslemek

• Put together = bir araya getirmek • Fine tüne = ince ayar
• Actually = gerçekten • Ability = yetenek
• Multi stage = çok aşamalı
• involve = içermek
• It typically involves use of GPUs and GPU clusters, and may take days, weeks or
even months (especially the pre-training step).
• Here's how it happens:
• Pre-training (Self-supervised Learning): This is the initial stage where the LLM
is exposed to a vast amount of unlabeled text data like books, articles, and
code.
• The model isn't given specific tasks but learns by predicting the next word in a
sequence or filling in missing pieces of text.
• This helps the LLM grasp the overall structure and patterns of language.
• Fine-tuning (Supervised Learning): After pre-training, the LLM is focused on
specific tasks through supervised learning.
• Here, labeled data with clear inputs and desired outputs is used.
• Take = sürmek • Grasp = kavramak
• Expose = maruz kalmak • Through = yoluyla
• Unlabeled = etiketlenmemiş • Supervised = denetimli
• Cluster = küme • Clear = net
• Fill = doldurmak
• Missing = eksik
• Overall = genel
• The model learns by comparing its generated responses to the correct outputs,
refining its ability to perform tasks like question answering or writing different
kinds of creative content.
• Why do we need these two stages? After the pre-training stage, an LLM would
have a good grasp of language mechanics but wouldn't necessarily understand
the meaning or real-world applications of language.
• Think of it as a child who's learned the alphabet and can sound out words but
doesn't understand the stories those words create.
• Here's an example: You ask the LLM to complete the sentence "The cat sat on
the..."
• After pre-training, the LLM might be good at predicting upcoming letters based
on patterns. It could respond with "...mat," a common word following "the cat
sat on."
• …
• However, it wouldn't necessarily understand the concept of a cat or a mat, nor
the physical possibility of a cat sitting on it.
• It would simply be using its statistical knowledge of what word typically follows
that sequence.
• This is a vital thing to understand. LLMs are not magical. They are simply built
on a neural network model that’s great at predicting the next word (rather,
token) after it has been trained.
• At this point, it's worthwhile understanding the meaning of a ‘token’, as you
would come across this in AI literature quite often.
• Tokens are the smallest units of meaning in a language. In Natural Language
Processing (NLP), tokens are typically created by dividing a sentence (or a
document) into words or other meaningful units like phrases based on the
tokenization algorithm used.
• Token = belirteç
• Therefore, the tokenization process involves converting text into a series of
tokens.
• Now, think about it. Language in our world works in a similar way. When
constructing a sentence, we start with a character or a word.
• Once we have the first word, the next word (or character, or phrase) is chosen
by us from a finite number of possible words (or characters, or phrases) that
we could use, and so on. And this is how a sentence eventually comes
together.
• This approach has come to be known as ‘next token prediction’, and is
incredibly powerful.
• Researchers are applying this approach to a range of other domains, and it is
giving miraculous results. For instance, researchers at Meta recently used this
technique to train an AI model to understand a 3D scene.
• …
• A 3D scene, if you think about it, can also be sequential. You have a wall, next
to which you have a door, above which you have a ceiling, and below which
you have a floor.
• So, if an AI model is able to predict the next word, why can’t it predict the next
object in a scene?
• A similar example is that of code. Code is entirely sequential. When you train
LLMs on code, they learn to predict the next ‘token’, in a very similar way that
it learned to predict the next word.
• Now, if pre-training has already trained the LLM to predict the next word (or,
token), why do we need to ‘fine-tune’ it?

• …