GPT-4 is a Transformer-based model introduced by OpenAI in March 2023. The original multimodal model accepts text and image inputs and produces text outputs.

Main changes

  • Adds image input to text input
  • Improves performance on many academic benchmarks compared with GPT-3 and GPT-3.5
  • Produces more detailed answers on complex tasks

Model size and training data

ClaimStatus
1.7 trillion parametersUnconfirmed estimate
45 terabytes of training dataUnconfirmed claim
Exact parameter count and training-data sizeOmitted from the public technical report

The public report describes next-token pre-training and RLHF fine-tuning. It withholds the detailed architecture and model size. GPT-4 technical report

Treat the size estimates as uncertain. Compare published capabilities directly when studying GPT-3 and GPT-4.

See Generative Pre-trained Transformer (GPT) for the model family and ChatGPT for the dialogue system.