templates/feature-extraction

1---2tags:3- feature-extraction4library_name: generic5---6 7# Feature Extraction repository template8 9This is a template repository for feature extraction to support generic inference with Hugging Face Hub generic Inference API. There are two required steps10 111. Specify the requirements by defining a `requirements.txt` file.122. Implement the `pipeline.py` `__init__` and `__call__` methods. These methods are called by the Inference API. The `__init__` method should load the model and preload all the elements needed for inference (model, processors, tokenizers, etc.). This is only called once. The `__call__` method performs the actual inference. Make sure to follow the same input/output specifications defined in the template for the pipeline to work.13 14Example repos15* https://huggingface.co/osanseviero/fasttext_english16 17## How to start18First create a repo in https://hf.co/new. 19Then clone this template and push it to your repo.20```21git clone https://huggingface.co/templates/feature-extraction22cd feature-extraction23git remote set-url origin https://huggingface.co/$YOUR_USER/$YOUR_REPO_NAME24git push --force25```