File size: 1,004 Bytes
9327b57 4d500b9 9327b57 4d500b9 9327b57 f7130c4 9327b57 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 |
import torch
from typing import Dict, List, Any
from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
# get dtype
dtype = torch.bfloat16 if torch.cuda.get_device_capability()[0] == 8 else torch.float16
class EndpointHandler:
def __init__(self, path=""):
# 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
|