handler.py

import torch
from typing import Dict, List, Any
from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline, BitsAndBytesConfig


class EndpointHandler:
    def __init__(self, path=""):
        bnb_config = BitsAndBytesConfig(
            load_in_4bit=True,
            bnb_4bit_use_double_quant=True,
            bnb_4bit_quant_type="nf4",
            bnb_4bit_compute_dtype=torch.bfloat16
        )
        # load the model
        tokenizer = AutoTokenizer.from_pretrained(path)
        model = AutoModelForCausalLM.from_pretrained(path, device_map="auto", quantization_config=bnb_config)
        # create inference pipeline
        self.pipeline = pipeline("text-generation", model=model, tokenizer=tokenizer, torch_dtype=torch.bfloat16)

    def __call__(self, data: Any):
        inputs = data.pop("inputs", data)
        prediction = self.pipeline(inputs)            
        
        # postprocess the prediction
        return prediction