← Back to Data Science

All Topics

Advertisement

Learn/Data Science/Deep Learning

GPT Models

Topic: LLM

Advertisement

Generative Pre-Training

GPT: decoder-only transformers.

GPT-1/2/3/4

GPT-1: 117M params. GPT-2: 1.5B. GPT-3: 175B. GPT-4: multimodal.

Training

Next token prediction. Large-scale text. Few-shot learning.

In-Context Learning

Prompt engineering. Examples in context. No gradient updates.

Key Takeaways

  1. GPT: auto-regressive decoder
  2. Few-shot via prompting
  3. Scale drives capabilities

Advertisement

Advertisement

Need More Practice?

Get personalized data science help from ChatWhole's AI-powered platform.

Get Expert Help →