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
- 22,230
This model does not have enough activity to be deployed to Inference API (serverless) yet.
Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.