cosql / handler.py
seedelano's picture
Update handler.py (#1)
e608d25
raw
history blame
980 Bytes
import torch
from typing import Dict, List, Any
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM, pipeline
# check for GPU
device = 0 if torch.cuda.is_available() else -1
class EndpointHandler():
def __init__(self, path=""):
# load the model
tokenizer = AutoTokenizer.from_pretrained(path)
model = AutoModelForSeq2SeqLM.from_pretrained(path ,low_cpu_mem_usage=True)
# create inference pipeline
self.pipeline = pipeline("text2text-generation", model=model, tokenizer=tokenizer,device=device)
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