|
import torch |
|
from typing import Dict, List, Any |
|
from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline |
|
|
|
|
|
|
|
dtype = torch.bfloat16 if torch.cuda.get_device_capability()[0] == 8 else torch.float16 |
|
|
|
|
|
class EndpointHandler: |
|
def __init__(self, path=""): |
|
|
|
tokenizer = AutoTokenizer.from_pretrained(path) |
|
model = AutoModelForCausalLM.from_pretrained(path, device_map="auto", torch_dtype=dtype, trust_remote_code=True) |
|
model.to('cuda:0') |
|
|
|
|
|
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) |
|
|
|
|
|
if parameters is not None: |
|
prediction = self.pipeline(inputs, max_new_tokens=2048, **parameters) |
|
else: |
|
prediction = self.pipeline(inputs) |
|
|
|
return prediction |
