Update README.md
Browse filesThe National Library of Sweden/KBLab releases a robust, multi-label sentiment classifier finetuned on [Megatron-BERT-large-165K](https://huggingface.co/KBLab/megatron-bert-large-swedish-cased-165k). The model was trained on approximately 75K Swedish texts from multiple linguistic domains and datasets. More information on the datasets will be published on [the KBLab blog](https://kb-labb.github.io/).
The model has a binary sister version trained on the same dataset. The binary model is to be uploaded soon.