WizardLM
WizardLM copied to clipboard
Do you apply ablation study on wizardcoder with fine tuning with initial code alpaca?
In ablation study, you show multi round revision works better than single round revision. You also show wizardcoder outperforms Pretrained model starcoder. However, it is unknown how much wizardcoder benefits from code alpaca or multi round prompt revision.
same question.
Same question ...