Instructions to use visual-ds/bert-mini-hatexplain with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use visual-ds/bert-mini-hatexplain with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="visual-ds/bert-mini-hatexplain")# Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("visual-ds/bert-mini-hatexplain") model = AutoModelForMaskedLM.from_pretrained("visual-ds/bert-mini-hatexplain", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| license: cc-by-4.0 | |
| Model of the paper: | |
| > [Lucas E. Resck](https://lucasresck.github.io/), [Marcos M. Raimundo](https://ic.unicamp.br/docente/marcos-medeiros-raimundo/), [Jorge Poco](http://visualdslab.com/~jpocom/). "Exploring the Trade-off Between Model Performance and Explanation Plausibility of Text Classifiers Using Human Rationales," **NAACL Findings 2024** (to appear). | |
| Refer to https://github.com/visual-ds/plausible-nlp-explanations. | |