Instructions to use nihalbaig/setfit_bn_hatespeech with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nihalbaig/setfit_bn_hatespeech with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="nihalbaig/setfit_bn_hatespeech")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("nihalbaig/setfit_bn_hatespeech") model = AutoModel.from_pretrained("nihalbaig/setfit_bn_hatespeech", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download handler.py from nihalbaig/setfit_bn_hatespeech: direct link, hf CLI and curl.
- Browser
- Download file 848 Bytes
-
https://huggingface.co/nihalbaig/setfit_bn_hatespeech/resolve/main/handler.py
- Command line
-
hf download hf://nihalbaig/setfit_bn_hatespeech/handler.py
-
curl -L -o handler.py https://huggingface.co/nihalbaig/setfit_bn_hatespeech/resolve/main/handler.py
848 Bytes
| from typing import Dict, List, Any | |
| from setfit import SetFitModel | |
| class EndpointHandler: | |
| def __init__(self, path=""): | |
| # load model | |
| self.model = SetFitModel.from_pretrained(path) | |
| # ag_news id to label mapping | |
| self.id2label = {0: "No Hate", 1: "Hate Speech"} | |
| def __call__(self, data: Dict[str, Any]) -> List[Dict[str, Any]]: | |
| """ | |
| data args: | |
| inputs (:obj: `str`) | |
| Return: | |
| A :obj:`list` | `dict`: will be serialized and returned | |
| """ | |
| # get inputs | |
| inputs = data.pop("inputs", data) | |
| if isinstance(inputs, str): | |
| inputs = [inputs] | |
| # run normal prediction | |
| scores = self.model.predict_proba(inputs)[0] | |
| return [{"label": self.id2label[i], "score": score.item()} for i, score in enumerate(scores)] |