Instructions to use cardiffnlp/twitter-roberta-base-hate with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use cardiffnlp/twitter-roberta-base-hate with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="cardiffnlp/twitter-roberta-base-hate")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("cardiffnlp/twitter-roberta-base-hate") model = AutoModelForSequenceClassification.from_pretrained("cardiffnlp/twitter-roberta-base-hate") - Inference
- Notebooks
- Google Colab
- Kaggle
This doesn't work at all?
#1
by M3LBY - opened
I don't know if I am confused about what this is supposed to detect, but basically anything I can think of that is hateful/racist/discriminatory does not register as hate speech. I can't get anything to be labeled as hate. Even when using slurs. Perhaps someone can clarify?
Thanks
I meet the same issue as you, now I am really confused about this model prediction.