Giters

nlpxucan / WizardLM

LLMs build upon Evol Insturct: WizardLM, WizardCoder, WizardMath

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

DS-1000 evaluation

TahaBinhuraib opened this issue · comments

commented

The paper presented evaluations on the ds-1000 benchmark, but I can't find a script to reproduce the results. It would be quite helpful if you could provide the code for evaluating these models on the ds1000 benchmark.