handler.py

from typing import Dict, List, Any
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel, PeftConfig
import torch


class EndpointHandler:
    def __init__(self, path=""):
        # load model and processor from path
        model = AutoModelForCausalLM.from_pretrained(
            path, torch_dtype=torch.float16, load_in_8bit=True, device_map="auto"
        )
        self.tokenizer = AutoTokenizer.from_pretrained(path)
        self.model.eval()

    def __call__(self, data: Dict[str, Any]) -> Dict[str, str]:
        '''
        Args:
            data (:dict:):
                The payload with the text prompt and generation parameters.
        '''
        # process input
        inputs = data.pop("inputs", data)
        parameters = data.pop("parameters", None)

        # preprocess
        input_ids = self.tokenizer(inputs, return_tensors="pt").input_ids

        # pass inputs with all kwargs in data
        if parameters is not None:
            outputs = self.model.generate(input_ids=input_ids, **parameters)
        else:
            outputs = self.model.generate(input_ids=input_ids)

        # postprocess the prediction
        prediction = self.tokenizer.decode(outputs[0], skip_special_tokens=True)

        return [{"generated_text": prediction}]