search

4AI / LS-LLaMA

A Simple but Powerful SOTA NER Model | Official Code For Label Supervised LLaMA Finetuning
https://arxiv.org/abs/2310.01208
MIT License
131 stars 20 forks source link

Padding Strategy #14

Open upjabir opened 6 months ago

upjabir commented 6 months ago

May i know what padding strategy that you had used?

SeanLee97 commented 5 months ago

@upjabir, sorry for the delayed reply. For the classification task, we use the last token strategy.