wasiahmad / PLBART

Official code of our work, Unified Pre-training for Program Understanding and Generation [NAACL 2021].
https://arxiv.org/abs/2103.06333
MIT License
186 stars 35 forks source link

plbart-large window size #49

Closed alibrahimzada closed 1 year ago

alibrahimzada commented 1 year ago

I believe there is something wrong with the window size (n_positions) of plbart-large. It prints the following:

>>> from transformers import PLBartTokenizer
>>> tokenizer = PLBartTokenizer.from_pretrained("uclanlp/plbart-large")
>>> tokenizer.model_max_length
1000000000000000019884624838656

I will be statically setting this to 1024.

wasiahmad commented 1 year ago

Can you raise the issue in Huggingface transformers? I do not have knowledge about the model_max_length field.

alibrahimzada commented 1 year ago

reported issue in HuggingFace.