google-deepmind / opro

official code for "Large Language Models as Optimizers"

Home Page:https://arxiv.org/abs/2309.03409

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

he instruction position should be either before the question, or at the beginning of the question, at the end of the question, or at the beginning of the answer.

wac81 opened this issue · comments

File "/nvme/opro/opro/optimization/optimize_instructions.py", line 178, in main
assert instruction_pos in {
AssertionError: The instruction position should be either before the question, or at the beginning of the question, at the end of the question, or at the beginning of the answer.

got error after run:
python optimize_instructions.py --optimizer="gpt-3.5-turbo" --scorer="text-bison" --instruction_pos="Q_beginning" --dataset="gsm8k" --task="train" --palm_api_key="<your_palm_api_key>" --openai_api_key="<your_openai_api_key>"

Thanks for catching the typo! I've updated the example command in README. Please change Q_beginning to Q_begin.

thanks