File size: 1,052 Bytes
1aeb34c c1cb360 fe371ad 1aeb34c c1cb360 5d540d6 c1cb360 7e91a22 c1cb360 b3aebd1 c1cb360 1aeb34c b3aebd1 1aeb34c c1cb360 b3aebd1 c1cb360 1aeb34c c1cb360 |
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 |
import torch
from typing import Dict, List, Any
from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
class EndpointHandler:
def __init__(self, path=""):
# load the model
tokenizer = AutoTokenizer.from_pretrained("microsoft/Phi-3-mini-128k-instruct")
model = AutoModelForCausalLM.from_pretrained(
"microsoft/Phi-3-mini-128k-instruct",
device_map="cuda",
torch_dtype="auto",
trust_remote_code=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 |