File size: 1,117 Bytes
6566cee e0f83a4 6566cee 46ed7eb 6566cee 5ee8ed9 f9a0290 e234444 46ed7eb 6566cee 742a64f 6566cee ea8887e 6566cee | 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 29 30 | import torch
from typing import Dict, List, Any
from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
# testing changes
# 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, trust_remote_code=True)
model.to('cuda:0')
# create inference pipeline
self.pipeline = pipeline("text-generation", model=model, tokenizer=tokenizer, device='cuda:0')
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, max_new_tokens=2048, **parameters)
else:
prediction = self.pipeline(inputs)
# postprocess the prediction
return prediction |