Code for "Small Models are Valuable Plug-ins for Large Language Models".
pip install -r requirements.txtcp api_config_example.py api_config.py
vi api_config.pypython run_glue.py \
--model_path roberta-large-mnli \
--model_name RoBERTa-Large \
--dataset mnli-m \
--explanation # Include this to enable explanation for overridesFor all supported tasks, see here.
For the complete set of parameters, see the code here.
python run_xnli.py \
--model_path /path/to/model \
--model_name XLM-V \
--lang en,ar,bg,de,el,es,fr,hi,ru,sw,th,tr,ur,vi,zh For the complete set of parameters, see the code here.
@article{xu2023small,
title={Small Models are Valuable Plug-ins for Large Language Models},
author={Canwen Xu and Yichong Xu and Shuohang Wang and Yang Liu and Chenguang Zhu and Julian McAuley},
journal={arXiv preprint arXiv:2305.08848},
year={2023}
}