|
Training workflow of original ChatGPT/InstructGPT release [15][16] ChatGPT is based on GPT foundation models that have been fine-tuned for conversational assistance. The fine-tuning process involved supervised learning and reinforcement learning from human feedback (RLHF). [17] Both approaches employed human trainers to improve model performance. In the case of supervised learning the ...
https://en.wikipedia.org/wiki/ChatGPT
|