ZhaofengWu/transparency-models

Pretrained model for our paper (https://arxiv.org/abs/2210.07468)

@inproceedings{wu-etal-2022-continued,
    title = "Transparency Helps Reveal When Language Models Learn Meaning",
    author = "Zhaofeng Wu and William Merrill and Hao Peng and Iz Beltagy and Noah A. Smith",
    url = {https://arxiv.org/abs/2210.07468},
    publisher = {arXiv},
    year = {2022},
    doi = {10.48550/ARXIV.2210.07468},
}

Please see the "Files and versions" tab for the models.