What is LLM?

Note

Hey guys, this is my personal reading note. I am not sure there might be some mistakes in my understanding. Please feel free to correct me (hsiangjenli@gmail.com) if you find any. Thanks!

The difference between GPT family [1]

ChatGPT V.S. GPT models

• ChatGPT is an application of GPT models (GPT-3, GPT-3.5, GPT-4, etc.)

GPT models

Publish Year	Model	Parameters	Reference
2019	GPT-2	1.5B	[6]
2020	GPT-3	175B	[2]
2022	GPT-3.5	175B	[3]
2023	GPT-4	Unknown	X
2024.05	GPT-4o	Unknown	[5]
2024.07	GPT-4o-mini	Unknown	[4]

Reference

[1]

GPT Base, GPT-3.5 Turbo & GPT-4: What's the difference? — pluralsight.com. https://www.pluralsight.com/resources/blog/ai-and-data/ai-gpt-models-differences. [Accessed 05-09-2024].

[2] (1,2)

Tom B Brown. Language models are few-shot learners. arXiv preprint arXiv:2005.14165, 2020.

[3]

Emmanuel Chude. GPT-3.5 and GPT-4 Comparison: Exploring the Developments in AI-Language Models — emmanuelchude.hashnode.dev. https://emmanuelchude.hashnode.dev/gpt-35-and-gpt-4-comparison-exploring-the-developments-in-ai-language-models. [Accessed 05-09-2024].

[4]

OpenAI. GPT-4o mini: advancing cost-efficient intelligence. https://openai.com/index/gpt-4o-mini-advancing-cost-efficient-intelligence/. [Accessed 05-09-2024].

[5]

OpenAI. Hello GPT-4o. https://openai.com/index/hello-gpt-4o/. [Accessed 05-09-2024].

[6] (1,2)

Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, Ilya Sutskever, and others. Language models are unsupervised multitask learners. OpenAI blog, 1(8):9, 2019.