Update execute.py

typo, update README

bugfix: input and output should support List[str], not just a single str

Update README.md

bugfix: datasets.Sequence -> datasets.Features

merge inputs into references

merge inputs into references

Update README.md

Update README.md

Update README.md

fix gradio sdk

Update README.md (#1)

update readme

update readme and description

bugfix: import numpy needs putenv and getcwd

update README

update naming

stdio format

rename code_eval -> code_eval_stdio

clone code_eval

initial commit