Tag: AI Alignment
-
RLHF Review: InstructGPT and Human Feedback Training
How InstructGPT's 1.3B model with RLHF beats 175B GPT-3. Full breakdown of SFT, reward modeling, and PPO training โ with the catches they skip.
How InstructGPT's 1.3B model with RLHF beats 175B GPT-3. Full breakdown of SFT, reward modeling, and PPO training โ with the catches they skip.