| from typing import Dict, List, Any | |
| from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline | |
| from peft import PeftModel | |
| import os | |
| class EndpointHandler(): | |
| def __init__(self, path=""): | |
| HF_TOKEN = os.getenv("HF_TOKEN") | |
| model = AutoModelForCausalLM.from_pretrained( | |
| "meta-llama/Llama-3.1-8B-Instruct", | |
| torch_dtype=None, | |
| device_map="auto", | |
| token=HF_TOKEN | |
| ) | |
| tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-3.1-8B-Instruct", trust_remote_code=True, token=HF_TOKEN) | |
| model = PeftModel.from_pretrained(model, path) | |
| model = model.merge_and_unload() | |
| 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) | |
| if parameters is not None: | |
| prediction = self.pipeline(inputs, **parameters) | |
| else: | |
| prediction = self.pipeline(inputs) | |
| return prediction |