IBM / transition-amr-parser

SoTA Abstract Meaning Representation (AMR) parsing with word-node alignments in Pytorch. Includes checkpoints and other tools such as statistical significance Smatch.
Apache License 2.0
246 stars 48 forks source link

Default directories #58

Open Ankushr785 opened 2 months ago

Ankushr785 commented 2 months ago

Is there a way to change the directory for this step: ----------loading pretrained bart.large model ----------

Because it seems to be downloading the pretrained weights to the same default directory no matter the changes i make to the code.