use adapter to inference

[zhanghanweii]

I use LORA to train the NER task, use crf for decoding, after saving adapter and head, the output dimension obtained by model.load_adapter() method when the model is called is 768, only after adding model.load_adapter() to model.load_head() to get the correct output dimension (equal to the number of tags in my category)

[adapter-hub-bert]

This issue has been automatically marked as stale because it has been without activity for 90 days. This issue will be closed in 14 days unless you comment or remove the stale label.

[adapter-hub-bert]

This issue was closed because it was stale for 14 days without any activity.