File size: 1,633 Bytes
a56b530 125bab8 a56b530 125bab8 a56b530 |
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 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 |
from typing import Any, Dict
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftConfig, PeftModel
from transformers import pipeline
class EndpointHandler:
def __init__(self, path=""):
# load model and processor from path
self.device = "cuda" if torch.cuda.is_available() else "cpu"
config = PeftConfig.from_pretrained(path)
model = AutoModelForCausalLM.from_pretrained(
config.base_model_name_or_path,
return_dict=True,
torch_dtype=torch.float16,
trust_remote_code=True,
)
self.tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path, trust_remote_code=True)
model = PeftModel.from_pretrained(model, path)
self.model = model
self.model.to(torch.float16)
self.model.to(self.device)
self.model = self.model.merge_and_unload()
self.model.eval()
self.pipeline = pipeline('text-generation',
model = self.model,
tokenizer=self.tokenizer,
device=self.device,
torch_dtype=torch.float16)
def __call__(self, data: Dict[str, Any]) -> Dict[str, str]:
# process input
inputs = data.pop("inputs", data)
parameters = data.pop("parameters", None)
# pass inputs with all kwargs in data
if parameters is not None:
outputs = self.pipeline(inputs, **parameters)
else:
outputs = self.pipeline(inputs)
return outputs |