# Multiclass vs Multilabel **URL:** \ **Category:** Beginners\ **Created:** [August 11, 2020, 8:29am UTC](https://discuss.huggingface.co/t/multiclass-vs-multilabel/672 "2020-08-11T08:29:13Z")\ **Posts on this page:** 2\ **Page:** 1
**Author:** ![lucaseo](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/lucaseo/32/250_2.png) [@lucaseo](https://discuss.huggingface.co/u/lucaseo)\ **Post date:** [August 11, 2020, 8:29am UTC](https://discuss.huggingface.co/t/multiclass-vs-multilabel/672/1 "2020-08-11T08:29:13Z")
Hello all, I’m relatively new to transformer library and its models. What I’m try-out is fine-tuning pretrained model for classification task. I understood that BertForSequenceClassification is for classical **multi-class** classification. However, I’m confused on how to achieve “multi-label” classification task. Can anyone guide me to multilabel classification? ps.) What I mean by Multiclass, it means labels are exclusive to each other ex) - num\_labels = 5 - labels=[0, 1, 0, 0, 0] Multilabel - num\_labels = 5 - labels = [1, 0, 0, 1, 0] ---
**Author:** ![marrrcin](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/marrrcin/32/12238_2.png) [@marrrcin](https://discuss.huggingface.co/u/marrrcin)\ **Post date:** [August 11, 2020, 9:26am UTC](https://discuss.huggingface.co/t/multiclass-vs-multilabel/672/2 "2020-08-11T09:26:17Z")
See how `transformers.modeling_bert.BertForSequenceClassification` is implemented - there is a `CrossEntropyLoss` built into this class internally. You can create custom class (PyTorch module) similar to `BertForSequenceClassification` and apply multi-label loss of your choice there. You can also look-up my blogpost [https://zablo.net/blog/post/custom-classifier-on-bert-model-guide-polemo2-sentiment-analysis/](https://zablo.net/blog/post/custom-classifier-on-bert-model-guide-polemo2-sentiment-analysis/) where I show how to build totally custom model on top of the pre-trained transformers models.