This is pre-trained model for offensive and hateful speech multiclassification. Model is fine-tuned on distilroberta-base model from the huggingface repository. This model is pre-trained on my original datasets. Reported accuracy of this model is 94.50%.
You can find all the datasets on this repository. Find out my Space on this model here.
You can find training notebook on my github profile @purveshpatel511. Report any bugs or issue here.
Checkout my GitHub Profile @purveshpatel511.
- Downloads last month
- 1,203