handler.py

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

# get dtype
dtype = torch.bfloat16 if torch.cuda.get_device_capability()[0] == 8 else torch.float16


class EndpointHandler:
    def __init__(self, path=""):

        config = PeftConfig.from_pretrained(path)
        model = AutoModelForCausalLM.from_pretrained(config.base_model_name_or_path, return_dict=True, load_in_8bit=True, device_map='auto')
        tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path)
        # Load the Lora model
        model = PeftModel.from_pretrained(model, path)
        if tokenizer.pad_token_id is None:
            tokenizer.pad_token = tokenizer.eos_token
            
        tokenizer.padding_side = "left"
        
        # load the model
        # tokenizer = AutoTokenizer.from_pretrained(path)
        # model = AutoModelForCausalLM.from_pretrained(path, device_map="auto", torch_dtype=dtype)

        
        # create inference pipeline
        self.pipeline = pipeline("text-generation", model=model, tokenizer=tokenizer)

    def __call__(self, data: Any) -> List[List[Dict[str, float]]]:
        inputs = data.pop("inputs", data)
        parameters = data.pop("parameters", None)

        # pass inputs with all kwargs in data
        if parameters is not None:
            prediction = self.pipeline(inputs, **parameters)
        else:
            prediction = self.pipeline(inputs)
        # postprocess the prediction
        return prediction