hard20 pts · first answer countsalignmentfine-tuning
How DPO differs from PPO-based RLHF
How does Direct Preference Optimization (DPO) differ from classic PPO-based RLHF?
Discussion 0
Join free to post in the discussion.
Related questions
- Trainable parameters in a LoRA adapterMachine Learning Engineer
- Fine-tuning a CNN with batch size 2Machine Learning Engineer
- Fine-tuned model forgets general skillsMachine Learning Engineer
- Knowledge that changes every dayAI Engineer (LLM & Generative AI)
- What LoRA trainsAI Engineer (LLM & Generative AI)
- Counting LoRA parametersAI Engineer (LLM & Generative AI)
- Fine-tuned model scores too wellAI Engineer (LLM & Generative AI)
- Fresh facts plus a fixed stylePrompt Engineer