File size: 1,252 Bytes
c1cb360
 
6d33a5e
fe371ad
 
1aeb34c
6d33a5e
b47e2d8
c1cb360
b47e2d8
6d33a5e
 
e8628b3
6d33a5e
e126c73
b3aebd1
6d33a5e
1aeb34c
6d33a5e
1e592e3
6d33a5e
 
 
 
 
1e592e3
6d33a5e
b47e2d8
eff3ac4
 
 
 
 
 
 
 
 
 
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
from typing import Dict, List, Any
from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
device = "cuda"

class EndpointHandler:
    def __init__(self, path=""):
        # load the model
        tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2-1.5B-Instruct")
        model = AutoModelForCausalLM.from_pretrained(
            "Qwen/Qwen2-1.5B-Instruct",
            torch_dtype="auto",
            device_map="auto"
        )
        # 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

# Example usage
if __name__ == "__main__":
    handler = EndpointHandler()
    data = {
        "inputs": "Hello, how can I",
        "parameters": {"max_length": 50, "num_return_sequences": 1}
    }
    result = handler(data)
    print(result)