Official PyTorch implementation of LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understanding (ACL 2022)
MIT License
335
stars
40
forks
source link
how to get the lilt-only-base using new model_args #20
Hi,
(1) You need to change max_2d_position_embedding setting in config file;
(2) You need to modify the 2d position embedding weight in the checkpoint.
if I change the max_2d_position_embeddings, how to get the lilt-only-base using new model_args