| from typing import Dict, List, Any | |
| from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline | |
| class EndpointHandler: | |
| def __init__(self, path=""): | |
| # load the model | |
| tokenizer = AutoTokenizer.from_pretrained(path) | |
| model = AutoModelForCausalLM.from_pretrained(path, device_map="auto") | |
| # create inference pipeline | |
| self.pipeline = pipeline("text-generation", model=model, tokenizer=tokenizer) | |
| def __call__(self, data: Any): | |
| inputs = data.pop("inputs", data) | |
| prediction = self.pipeline(inputs) | |
| # postprocess the prediction | |
| return prediction | |