File size: 1,519 Bytes
715997e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5677d77
 
 
 
 
 
 
 
 
 
 
 
 
 
 
715997e
5677d77
bbec848
 
 
 
5677d77
bbec848
715997e
 
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
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
Hugging Face's logo
Hugging Face
Search models, datasets, users...
Models
Datasets
Spaces
Docs
Solutions
Pricing




ammarnasr
/
CodeGen2_1B_merged 

like
0
Text Generation
Transformers
PyTorch
codegen
custom_code
Inference Endpoints
Model card
Files and versions
Community
Settings
CodeGen2_1B_merged
/
handler.py
ammarnasr's picture
ammarnasr
Update handler.py
5f48ffc
7 minutes ago
raw
history
blame
edit
delete
1.06 kB
from typing import Any, Dict, List
import torch
import transformers
from transformers import AutoModelForCausalLM, AutoTokenizer

dtype = torch.bfloat16 if torch.cuda.get_device_capability()[0] ==8 else torch.float16

class EndpointHandler:
    def __init__(self, path=""):
        self.tokenizer = AutoTokenizer.from_pretrained(path)
        self.model = AutoModelForCausalLM.from_pretrained(path, trust_remote_code=True, revision="main")
        self.device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
        self.model = self.model.to(self.device)


    def __call__(self, data: Dict[str, Any]) -> Dict[str, Any]:
        prompt = data["inputs"]
        if "config" in data:
          config = data.pop("config", None)
        else:
          config = {'max_new_tokens':100}
        input_ids = self.tokenizer(prompt, return_tensors="pt").input_ids.to(self.device)
        generated_ids = self.model.generate(input_ids, **config)
        generated_text = self.tokenizer.decode(generated_ids[0], skip_special_tokens=True)
        return [{"generated_text": generated_text}]