File size: 4,844 Bytes
6351d80
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
import argparse
import torch

from llava.constants import IMAGE_TOKEN_INDEX, DEFAULT_IMAGE_TOKEN, DEFAULT_IM_START_TOKEN, DEFAULT_IM_END_TOKEN
from llava.conversation import conv_templates, SeparatorStyle
from llava.model.builder import load_pretrained_model
from llava.utils import disable_torch_init
from llava.mm_utils import process_images, tokenizer_image_token, get_model_name_from_path

from PIL import Image

import requests
from PIL import Image
from io import BytesIO
from transformers import TextStreamer


def load_image(image_file):
    if image_file.startswith('http://') or image_file.startswith('https://'):
        response = requests.get(image_file)
        image = Image.open(BytesIO(response.content)).convert('RGB')
    else:
        image = Image.open(image_file).convert('RGB')
    return image


def main(args):
    # Model
    disable_torch_init()

    model_name = get_model_name_from_path(args.model_path)
    tokenizer, model, image_processor, context_len = load_pretrained_model(args.model_path, args.model_base, model_name, args.load_8bit, args.load_4bit, device=args.device)

    if "llama-2" in model_name.lower():
        conv_mode = "llava_llama_2"
    elif "mistral" in model_name.lower():
        conv_mode = "mistral_instruct"
    elif "v1.6-34b" in model_name.lower():
        conv_mode = "chatml_direct"
    elif "v1" in model_name.lower():
        conv_mode = "llava_v1"
    elif "mpt" in model_name.lower():
        conv_mode = "mpt"
    else:
        conv_mode = "llava_v0"

    if args.conv_mode is not None and conv_mode != args.conv_mode:
        print('[WARNING] the auto inferred conversation mode is {}, while `--conv-mode` is {}, using {}'.format(conv_mode, args.conv_mode, args.conv_mode))
    else:
        args.conv_mode = conv_mode

    conv = conv_templates[args.conv_mode].copy()
    if "mpt" in model_name.lower():
        roles = ('user', 'assistant')
    else:
        roles = conv.roles

    image = load_image(args.image_file)
    image_size = image.size
    # Similar operation in model_worker.py
    image_tensor = process_images([image], image_processor, model.config)
    if type(image_tensor) is list:
        image_tensor = [image.to(model.device, dtype=torch.float16) for image in image_tensor]
    else:
        image_tensor = image_tensor.to(model.device, dtype=torch.float16)

    while True:
        try:
            inp = input(f"{roles[0]}: ")
        except EOFError:
            inp = ""
        if not inp:
            print("exit...")
            break

        print(f"{roles[1]}: ", end="")

        if image is not None:
            # first message
            if model.config.mm_use_im_start_end:
                inp = DEFAULT_IM_START_TOKEN + DEFAULT_IMAGE_TOKEN + DEFAULT_IM_END_TOKEN + '\n' + inp
            else:
                inp = DEFAULT_IMAGE_TOKEN + '\n' + inp
            image = None
        
        conv.append_message(conv.roles[0], inp)
        conv.append_message(conv.roles[1], None)
        prompt = conv.get_prompt()

        input_ids = tokenizer_image_token(prompt, tokenizer, IMAGE_TOKEN_INDEX, return_tensors='pt').unsqueeze(0).to(model.device)
        stop_str = conv.sep if conv.sep_style != SeparatorStyle.TWO else conv.sep2
        keywords = [stop_str]
        streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)

        with torch.inference_mode():
            output_ids = model.generate(
                input_ids,
                images=image_tensor,
                image_sizes=[image_size],
                do_sample=True if args.temperature > 0 else False,
                temperature=args.temperature,
                max_new_tokens=args.max_new_tokens,
                streamer=streamer,
                use_cache=True)

        outputs = tokenizer.decode(output_ids[0]).strip()
        conv.messages[-1][-1] = outputs

        if args.debug:
            print("\n", {"prompt": prompt, "outputs": outputs}, "\n")


if __name__ == "__main__":
    parser = argparse.ArgumentParser()
    parser.add_argument("--model-path", type=str, default="facebook/opt-350m")
    parser.add_argument("--model-base", type=str, default=None)
    parser.add_argument("--image-file", type=str, required=True)
    parser.add_argument("--device", type=str, default="cuda")
    parser.add_argument("--conv-mode", type=str, default=None)
    parser.add_argument("--temperature", type=float, default=0.2)
    parser.add_argument("--max-new-tokens", type=int, default=512)
    parser.add_argument("--load-8bit", action="store_true")
    parser.add_argument("--load-4bit", action="store_true")
    parser.add_argument("--debug", action="store_true")
    args = parser.parse_args()
    main(args)