I’m trying to fine-tune dslim/bert-base-NER using the wnut_17 dataset. Since the number of NER labels is different, I manually replaced these parameters in the model to get rid of the size mismatch error : model.config.id2label = my_id2label model.config.label2id = my_label2id model.config._num_…

Thank you @nielsr for being responsive. That error is resolved now, but the question is "does simply changing the number of labels mean that we have changed the classifier head?!" By the way, for my problem, I had to do these modifications: model_name = "dslim/bert-base-NER" mymodel = AutoModelFo…

Replacing last layer of a fine-tuned model to use different set of labels

Beginners

nielsr December 21, 2021, 1:55pm 2

Hi,

See this post that will solve your issue

Topic		Replies	Views
Replacing last layer of a fine-tuned model for using different set of labels Beginners	0	274	December 18, 2021
Retrain/reuse fine-tuned models on different set of labels Beginners	7	4225	April 8, 2021
Overall accuracy in Finetuning dslim/bert-base-NER with custom dataset and labels gets only up to ~0.15 using seqeval 🤗Transformers	2	338	May 1, 2023
How do I change the classification head of a model? 🤗Transformers	28	42400	June 8, 2023
Adjusting parameters for the FC layers at the end 🤗Transformers	1	1601	July 20, 2021

Replacing last layer of a fine-tuned model to use different set of labels

Related Topics