AI teams ; Favoris ; NLP: pretraining ; OpenAI AND RL from Human Feedback
Common descendants
2 Documents
Hyung Won Chung sur Twitter : "RLHF as an instance of using a learned objective function"
Tags:
2023-05-18 About
Prompting, Instruction Finetuning, and RLHF (CS224N)
Tags:
2023-02-16 About