Intro to LLMs – TamTam Learning

Course Prerequisite(s)

Please note that this course has the following prerequisites which must be completed before it can be accessed
Intro to NLP for AI

About Course

In recent years, large language models (LLMs) have dominated the tech news for their incredible ability to write poetry, essays, social media content, code, and more. They’re the hot new topic in natural language processing. This Intro to Large Language Models course teaches you the knowledge and skills required to experiment and create your own language model solutions. Through a combination of video lessons and practical coding exercises, we’ll cover what these language models are, their functions, and ways to implement them into your own projects. Whether you want to generate content, create a chatbot, or train these models on your own custom data and NLP tasks, this course equips you with the fundamental tools and concepts to fine-tune LLM models and tackle these challenges.

Create your own AI-driven applications tailored to solve specific business problems
Boost your career prospects by mastering AI Engineering skills
Gain a solid understanding of key LLM concepts such as attention and self-attention, crucial for building intuitive AI systems
Learn how to integrate Open AI’s API and create a bridge between your products and powerful AI foundation models
Get an introduction to LangChain, the platform that streamlines the creation of AI-driven apps
Explore HuggingFace to access the cutting-edge AI Engineering tools it offers

Course Content

1. Introduction to Large Language Models

1.1 Introduction to the course

02:21
1.2 Course Materials and Notebooks
1.3 What are LLMs

02:56
1.4 How large is an LLM

02:56
1.5 General purpose models

01:09
1.7 What can LLMs be used for

03:18

2. The Transformer Architecture

2.1 Deep learning recap

02:32
Exercise
2.2 The problem with RNNs

03:35
2.3 The solution attention is all you need

02:50
2.4 The transformer architecture

01:02
Exercise
2.5 Input embeddings

02:54
2.6 Multiheaded attention

03:59
Exercise
2.7 Feed-forward layer

02:38
2.8 Masked multihead attention

01:24
2.9 Predicting the final outputs

01:44

3. Getting started with GPT models

3.1 What does GPT mean

01:28
3.2 The development of ChatGPT

02:28
3.3 OpenAI API

02:58
3.4 Generating text

02:25
3.5 Customizing GPT Output

04:04
3.6 Key word text summarization

03:47
3.7 Coding a simple chatbot

06:17
3.8 Introduction to Langchain in Python

01:27
3.9 Langchain

02:49
3.10 Adding custom data to our chatbot

05:21

4. Hugging Face Transformers

5. Question and answer models with BERT

6. Text classification with XLNet

Course Project

Add this certificate to your resume to demonstrate your skills & increase your chances of getting noticed.

Student Ratings & Reviews

5.0

Total 3 Ratings

3 Ratings

0 Rating

10 months ago

Very ineteresting!

1 year ago

Good Course

Prosper Alikizang

1 year ago

Great course!

Course Prerequisite(s)

About Course

What Will You Learn?

Course Content

1. Introduction to Large Language Models

1.1 Introduction to the course

1.2 Course Materials and Notebooks

1.3 What are LLMs

1.4 How large is an LLM

1.5 General purpose models

1.7 What can LLMs be used for

2. The Transformer Architecture

2.1 Deep learning recap

Exercise

2.2 The problem with RNNs

2.3 The solution attention is all you need

2.4 The transformer architecture

Exercise

2.5 Input embeddings

2.6 Multiheaded attention

Exercise

2.7 Feed-forward layer

2.8 Masked multihead attention

2.9 Predicting the final outputs

3. Getting started with GPT models

3.1 What does GPT mean

3.2 The development of ChatGPT

3.3 OpenAI API

3.4 Generating text

3.5 Customizing GPT Output

3.6 Key word text summarization

3.7 Coding a simple chatbot

3.8 Introduction to Langchain in Python

3.9 Langchain

3.10 Adding custom data to our chatbot

4. Hugging Face Transformers

4.1 Hugging Face package

4.2 The transformer pipeline

4.3 Pretrained tokenizers

4.4 Special tokens

4.5 Hugging Face and PyTorch, TensorFlow

5. Question and answer models with BERT

5.1 GPT vs BERT

5.2 BERT architecture

5.3 Loading the model and tokenizer

5.4 BERT embeddings

5.5 Calculating the response

5.6 Creating a QA bot

5.7 BERT, RoBERTa, DistilBERT

6. Text classification with XLNet

6.1 GPT vs BERT vs XLNET

A note on the following lecture

6.2 Preprocessing our data

6.3 XLNet Embeddings

6.4 Fine tuning XLNet

6.5 Evaluating our model

Course Project

LLM Project: Text Generation & Chatbot

Earn a certificate

Student Ratings & Reviews

Quick Links