from transformers import AutoTokenizer, TextGenerationPipeline, pipeline | |
from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig | |
from typing import Dict, List, Any | |
class EndpointHandler: | |
def __init__(self, path=""): | |
# load the model | |
tokenizer = AutoTokenizer.from_pretrained(path) | |
model = AutoGPTQForCausalLM.from_quantized(path, device="cuda:0", use_safetensors=True) | |
# 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 | |