File size: 812 Bytes
558d19f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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

from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
import torch

class EndpointHandler:
    def __init__(self, path=""):
        self.tokenizer = AutoTokenizer.from_pretrained(path)
        self.model = AutoModelForCausalLM.from_pretrained(
            path,
            torch_dtype=torch.float16,
            device_map="auto",
        )
        self.pipeline = pipeline(
            "text-generation",
            model=self.model,
            tokenizer=self.tokenizer,
        )

    def __call__(self, data):
        inputs = data.get("inputs", "")
        parameters = data.get("parameters", {})
        
        if not parameters.get("max_new_tokens"):
            parameters["max_new_tokens"] = 2048
        
        result = self.pipeline(inputs, **parameters)
        return result