Landscape of Large Language Models

Text Analysis with large language models

Emi Tanaka

19th March 2025

These slides are best viewed on a modern browser like Google Chrome on a desktop or laptop. You can navigate the slides using the left and right arrows.

Table of contents

• Acknowledgement to Country
• Workshop materials
• 👋 Introductions
• How will it work?
• Schedule
• Landscape of Large Language Models
  • ChatGPT
  • ChatGPT Demo
  • Chatbot timeline
  • Related concepts
  • Rise of large language models
  • Using a LLM
  • Open AI models
  • Ollama
  • Which LLM to use?
• Exercise 1

Acknowledgement to Country

I’d like to begin by acknowledging the Traditional Owners of the land on which we meet today. I would also like to pay my respects to Elders past and present.

Ngunnawal people

Workshop materials

All materials will be hosted at
https://emitanaka.org/workshop-text-analysis-2025/

• Materials will still be available after the workshop.
• Contact emi.tanaka@anu.edu.au if you have any issues accessing the materials.

👋 Introductions

Presenter: Dr. Emi Tanaka

Please introduce yourself!

How will it work?

• Recordings will be distributed to all registrants after the workshop for a limited time (provided no technical issues in the recording)
• For those who do not wish to be recorded, we will pause the recording so it is not included in the final recording.

Schedule

Day	Perth	Adelaide	AEST	Duration	Content
Tue	11:00am	12:30pm	01:00pm	~30 mins	Landscape of Large Language Models
	11:30am	01:00pm	01:30pm	~30 mins	Exercise 1
	12:00pm	01:30pm	02:00pm	~25 mins	Capabilities of Large Language Models
	12:25pm	01:55pm	02:25pm	~30 mins	Exercise 2
	12:55pm	02:25pm	02:55pm	~15 mins	Break
	01:10pm	02:40pm	03:10pm	~25 mins	Parameters of Large Language Models
	01:35pm	03:05pm	03:35pm	~30 mins	Exercise 3
	02:05pm	03:35pm	04:05pm	~25 mins	Prompt Engineering
	02:30pm	04:00pm	04:30pm	~30 mins	Exercise 4
Wed	11:00am	12:30pm	01:00pm	~10 mins	Q&A
	11:10am	12:40pm	01:10pm	~20 mins	Processing unstructured data to structured data
	11:30am	01:00pm	01:30pm	~30 mins	Exercise 5
	12:00pm	01:30pm	02:00pm	~30 mins	Text analysis tasks
	12:30pm	02:00pm	02:30pm	~30 mins	Exercise 6
	01:00pm	02:30pm	03:00pm	~15 mins	Break
	01:15pm	02:45pm	03:15pm	~45 mins	Architecture of Large Language Models
	02:00pm	03:30pm	04:00pm	~50 mins	Exercise 7
	02:50pm	04:20pm	04:50pm	~10 mins	Next steps

Landscape of Large Language Models

ChatGPT

• ChatGPT was released to public on 30th November 2022.
• ChatGPT gained a staggering 100 million active users in 2 months¹.

ChatGPT Heralds an Intellectual Revolution

25 February 2023

By Henry Kissinger, Eric Schmidt, and Daniel Huttenlocher

Generative artificial intelligence presents a philosophical and practical challenge on a scale not experienced since the start of the Enlightenment.

A new technology bids to transform the human cognitive process as it has not been shaken up since the invention of printing. The technology that printed the Gutenberg Bible in 1455 made abstract human thought communicable generally and rapidly. But new technology today reverses that process. Whereas the printing press caused a profusion of modern human thought, the new technology achieves its distillation and elaboration. In the process, it creates a gap between human knowledge and human understanding. If we are to navigate this transformation successfully, new concepts of human thought and interaction with machines will need to be developed. This is the essential challenge of the Age of Artificial Intelligence.

…

Mr. Kissinger served as secretary of state, 1973-77, and White House national security adviser, 1969-75. Mr. Schmidt was CEO of Google, 2001-11 and executive chairman of Google and its successor, Alphabet Inc., 2011-17. Mr. Huttenlocher is dean of the Schwarzman College of Computing at the Massachusetts Institute of Technology. They are authors of “The Age of AI: And Our Human Future.” The authors thank Eleanor Runde for her research.

• GPT = Generative Pre-trained Transformer

1. Hu, Krystal (2023) ChatGPT sets record for fastest-growing user base - analyst note. Reuters.

ChatGPT Demo

https://chatgpt.com/

Chatbot timeline

Refresh of browser may be needed for timeline to render correctly

Data Source: https://en.wikipedia.org/wiki/List_of_chatbots (Accessed on 11/08/2024)

Related concepts

• Overlapping but different focuses often using related methods.

chat with user

multiple purposes

new creative content

• Note: not all LLMs power chatbots and genAI but most do.
• We’ll look at the architecture of LLM later in the workshop.

• A large language models (LLM) is a computational model capable of general-purpose language generation and other natural language processing (NLP) tasks.
• Most LLMs are artificial neural networks built with a decoder-only transformer-based architecture.
• Generative Pre-trained Transformers (GPT) are a type of LLM

Rise of large language models

Refresh of browser may be needed for timeline to render correctly

Data Source: https://en.wikipedia.org/wiki/Large_language_model#List (Accessed on 11/08/2024)

• A large language model (LLM) is a computational model notable for its ability to achieve general-purpose language generation and other natural language processing tasks such as classification.
• Generative pre-trained transformers (GPT) are a type of LLM.
• Generative artificial intelligence (GenAI) is artificial intelligence capable of generating new creative content.

Using a LLM

Provider API

…

• Requires internet access
• Requires account with provider
• Ongoing payment for usage

Local LLM

GPT4All LM Studio Jan llama.cpp llamafile Ollama NextChat …

• No internet access required
• No account required
• Several GB of hard disk space required
• At least 16GB RAM required for 7b parameter LLMs

Open AI models

Models:

• chatgpt-4o-latest
• gpt-4o
• gpt-4o-mini
• gpt-3.5-turbo
• dall-e-3
• text-embedding-ada-002
• tts-1-hd
• whisper-1
• …

• API access via cURL

curl https://api.openai.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [
      {
        "role": "system",
        "content": "You are a helpful assistant."
      },
      {
        "role": "user",
        "content": "Hello!"
      }
    ]
  }'

• Pricing can range from ~US$0.75 to ~US$75.00 per 1 million tokens depending on the model used.

Ollama

Models:

• llama3.2:1b
• llama3.2:3b
• llama3.1:8b
• llama3.1:70b
• llama3.1:405b
• gemma2:2b
• gemma2:9b
• gemma2:27b
• llava:7b
• …

curl http://localhost:11434/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "llama3.2:1b",
    "messages": [
      {
        "role": "system",
        "content": "You are a helpful assistant."
      },
      {
        "role": "user",
        "content": "Hello!"
      }
    ]
  }'

• Pricing: FREE.
• The model name has a suffix with the number of parameters, e.g. llama3.1:8b has about 8 billion parameters.
• Larger number of parameters requires larger RAM (~16GB RAM required for 7b).

Which LLM to use?

• LLM leaderboards, e.g. Open LLM Leaderboard and LLM Arena.
• Smaller number of model parameters may not perform as well for complex tasks.
  
• There are some specialised LLMs, e.g. 
  • dall-e-3 generates images from user text input
  • llava:7b is a multi-modal model and can take image input
  • mathstral:7b is designed for math reasoning and scientific discovery
  • deepseek-coder-v2:16b comparable to gpt-4-turbo in code-specific tasks
  • meditron:7b adapted from llama2 for medical domain
• Currently I use mostly:
  • Open AI: gpt-4o, gpt-4o-mini and dall-e-3 with payment of US$15 so far
  • Ollama: llama3.1:8b and llava:7b

Exercise 1

Go to Exercise 1

Next slide

Back to start