Instructions to use jimnoneill/xbox-compulsion-classifier with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- setfit
How to use jimnoneill/xbox-compulsion-classifier with setfit:
from setfit import SetFitModel model = SetFitModel.from_pretrained("jimnoneill/xbox-compulsion-classifier") preds = model.predict(["i loved the spiderman movie!", "pineapple on pizza is the worst"]) print(preds) - Notebooks
- Google Colab
- Kaggle
Point to archive version 2026.11.15
Browse files
README.md
CHANGED
|
@@ -98,8 +98,8 @@ TI7 for a post is the mean of seven positive-class probabilities: offensive lang
|
|
| 98 |
|
| 99 |
- Analysis code: https://github.com/jimnoneill/xbox-toxicity-index
|
| 100 |
- Training labels (with post text) and annotation: https://huggingface.co/datasets/jimnoneill/xbox-political-compulsion-dataset
|
| 101 |
-
- Software archive: https://doi.org/10.5281/zenodo.
|
| 102 |
-
- Derived results and annotation metadata, including the numeric training-label projections and per-classifier cutoffs: https://doi.org/10.5281/zenodo.
|
| 103 |
|
| 104 |
The `xbox/` package in this repository contains the scoring code and the analysis modules (stream hygiene, rhythm descriptors, roll-call location model, point-process models, binned count models and the forecasting experiments).
|
| 105 |
|
|
|
|
| 98 |
|
| 99 |
- Analysis code: https://github.com/jimnoneill/xbox-toxicity-index
|
| 100 |
- Training labels (with post text) and annotation: https://huggingface.co/datasets/jimnoneill/xbox-political-compulsion-dataset
|
| 101 |
+
- Software archive: https://doi.org/10.5281/zenodo.24252944 (version 2026.11.15)
|
| 102 |
+
- Derived results and annotation metadata, including the numeric training-label projections and per-classifier cutoffs: https://doi.org/10.5281/zenodo.24252949 (version 2026.11.15)
|
| 103 |
|
| 104 |
The `xbox/` package in this repository contains the scoring code and the analysis modules (stream hygiene, rhythm descriptors, roll-call location model, point-process models, binned count models and the forecasting experiments).
|
| 105 |
|