To reproduce OpenAI's performance on this task, use the following script:
bash script/openai/run.sh
You need to change the parameter settings in script/openai/run.sh
:
type
: Choose fromquarter
orfull
.model
: Model name.input_file
: File path of the dataset.answer_file
: Original answer in JSON format from GPT.parsing_file
: Post-process the output of GPT in JSONL format to obtain executable code segments.readme_type
: Choose fromoracle_segment
andreadme
.oracle_segment
: The code paragraph in the README that is most relevant to the task.readme
: The entire text of the README in the repository where the task is located.
engine_name
: Choose fromgpt-35-turbo-16k
andgpt-4-32
.n_turn
: Number of executable codes GPT returns (5 times in the paper experiment).openai_key
: Your OpenAI API key.