File size: 1,202 Bytes
3a31a5b
ba13b5a
0af1b4a
9bd5173
040e104
3a31a5b
 
ba13b5a
22bc6be
ba13b5a
 
 
040e104
22bc6be
0af1b4a
9bd5173
ba13b5a
22bc6be
ba13b5a
 
040e104
 
 
 
 
 
 
 
 
ba13b5a
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
import torch
from typing import Dict, List, Any
# from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline

# check for GPU
device = 0 if torch.cuda.is_available() else -1


class EndpointHandler:
    def __init__(self, path=""):
        # load the model
        tokenizer = AutoTokenizer.from_pretrained(path)
        # model = AutoModel.from_pretrained(path, low_cpu_mem_usage=True)
        # model = AutoModelForCausalLM.from_pretrained(path, low_cpu_mem_usage=True)
        model = AutoModelForCausalLM.from_pretrained(path, low_cpu_mem_usage=True)
        # create inference pipeline
        self.pipeline = pipeline("text-generation", model=model, tokenizer=tokenizer, device=device)

    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