Instructions to use k4tel/bert-geolocation-prediction with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use k4tel/bert-geolocation-prediction with Transformers:
# Load model directly from transformers import BertGeoRegressor model = BertGeoRegressor.from_pretrained("k4tel/bert-geolocation-prediction", dtype="auto") - Notebooks
- Google Colab
- Kaggle
| from typing import Dict, List, Any | |
| import torch | |
| from transformers import pipeline | |
| class EndpointHandler(): | |
| def __init__(self, path=""): | |
| self.pipeline = pipeline("geo-regression", model=path) | |
| def __call__(self, data: Dict[str, Any]) -> List[Dict[str, Any]]: | |
| """ | |
| data args: | |
| inputs (:obj: `str`) | |
| date (:obj: `str`) | |
| Return: | |
| A :obj:`list` | `dict`: will be serialized and returned | |
| """ | |
| # get inputs | |
| inputs = data.pop("inputs", data) | |
| # get additional date field | |
| date = data.pop("date", None) | |
| # check if date exists and if it is a holiday | |
| # run normal prediction | |
| prediction = self.pipeline(inputs) | |
| return prediction | |