Instructions to use unitary/toxic-bert with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use unitary/toxic-bert with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="unitary/toxic-bert")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("unitary/toxic-bert") model = AutoModelForSequenceClassification.from_pretrained("unitary/toxic-bert") - Inference
- Notebooks
- Google Colab
- Kaggle
Disclaimer no longer necessary?
#6
by umm-maybe - opened
It appears that the issue alluded to in the disclaimer on these models no longer exists. Might want to remove that as it could be confusing for people. Also as the detoxify library requires a different version of transformers which will conflict with the latest.