Fine Tuning
9 practice items · needed by 3 roles
Easy 0Medium 2Hard 7
Practice questions
- Trainable parameters in a LoRA adaptermedium
- Fine-tuning a CNN with batch size 2hard
- How DPO differs from PPO-based RLHFhard
- Fine-tuned model forgets general skillshard
- Knowledge that changes every daymedium
- What LoRA trainshard
- Counting LoRA parametershard
- Fine-tuned model scores too wellhard
- Fresh facts plus a fixed stylehard