Hatespeech models

This archive contains fine-tuned models trained for the engineering thesis project: - herbert-base-finetuned: fine-tuned from allegro/herbert-base-cased HerBERT [Mroczkowski et al., 2021]- herbert-large-hs-finetuned: fine-tuned from dkleczek/Polish-Hate-Speech-Detection-Herbert-Large- roberta-large-v2-finetuned: fine-tuned from sdadas/polish-roberta-large-v2 Polish RoBERTa [Dadas et al., 2020]- svm/svm_model.joblib: SVM baseline trained on TF-IDF features. Base models are available on Hugging Face and are not redistributed here in their original form. Please refer to their model cards for licensing and authorship. Mroczkowski R. et al., 2021. HerBERT: Efficiently Pretrained Transformer-based Language Model for Polish. BSNLP. Dadas S. et al., 2020. Pre-training Polish Transformer-based Language Models at Scale. ICAISC.