File size: 1,583 Bytes
7feaf20
 
 
6a72b4d
5701230
7feaf20
 
 
5701230
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
from typing import Dict, List, Any
from PIL import Image    
import requests
import torch
from transformers import AutoProcessor, LlavaForConditionalGeneration

class EndpointHandler():
    def __init__(self, path=""):
        model_id = ""
        model = LlavaForConditionalGeneration.from_pretrained(
        model_id, 
        torch_dtype=torch.float16, 
        low_cpu_mem_usage=True, 
        ).to(0)
        processor = AutoProcessor.from_pretrained(model_id)

    def __call__(self, data: Dict[str, Any]) -> List[Dict[str, Any]]:
        parameters = data.pop("inputs",data)
        inputs = data.pop("inputs", data)
        if parameters is not None:
            url = "http://images.cocodataset.org/val2017/000000039769.jpg"
            image = Image.open(requests.get(url, stream=True).raw)
            prompt = "USER: <image>\nWhat are these?\nASSISTANT:"
            output = model.generate(**inputs, max_new_tokens=200, do_sample=False)
        return output

    
prompt = "USER: <image>\nWhat are these?\nASSISTANT:"
image_file = "http://images.cocodataset.org/val2017/000000039769.jpg"

model = LlavaForConditionalGeneration.from_pretrained(
    model_id, 
    torch_dtype=torch.float16, 
    low_cpu_mem_usage=True, 
).to(0)

processor = AutoProcessor.from_pretrained(model_id)


raw_image = Image.open(requests.get(image_file, stream=True).raw)
inputs = processor(prompt, raw_image, return_tensors='pt').to(0, torch.float16)

output = model.generate(**inputs, max_new_tokens=200, do_sample=False)
print(processor.decode(output[0][2:], skip_special_tokens=True))