File size: 4,640 Bytes
a0a6a64
e02e941
a539d3b
a0a6a64
a539d3b
 
 
 
 
a0a6a64
a539d3b
a0a6a64
a539d3b
e02e941
a539d3b
 
 
e02e941
a539d3b
 
 
 
 
 
 
 
 
 
 
 
a0a6a64
 
e02e941
a539d3b
3e0b719
a539d3b
 
 
 
 
 
 
e02e941
a8ec507
 
 
 
16b4096
a539d3b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
16b4096
a539d3b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
128
129
130
131
132
133
134
135
136
137
138
import os
import torch
import spaces
import gradio as gr
from PIL import Image
from transformers.utils import move_cache
from huggingface_hub import snapshot_download
from transformers import AutoModelForCausalLM, AutoTokenizer


# Load the model and processor

MODEL_PATH = "THUDM/cogvlm2-llama3-chat-19B"

os.environ['HF_HUB_ENABLE_HF_TRANSFER'] = '1'
MODEL_PATH = snapshot_download(MODEL_PATH)
move_cache()

DEVICE = 'cuda' if torch.cuda.is_available() else 'cpu'
TORCH_TYPE = torch.bfloat16 if torch.cuda.is_available() and torch.cuda.get_device_capability()[0] >= 8 else torch.float16

tokenizer = AutoTokenizer.from_pretrained(
    MODEL_PATH,
    trust_remote_code=True
)
model = AutoModelForCausalLM.from_pretrained(
    MODEL_PATH,
    torch_dtype=TORCH_TYPE,
    trust_remote_code=True,
).to(DEVICE).eval()


@spaces.GPU
def generate_caption(image, prompt):
    
    # Process the image and the prompt
    text_only_template = "A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: {} ASSISTANT:"
    # inputs = processor(texts=[prompt], images=[image], return_tensors="pt").to('cuda') # move inputs to cuda


   
    return 


## make predictions via api ##
# https://www.gradio.app/guides/getting-started-with-the-python-client#connecting-a-general-gradio-app

demo = gr.Interface(
    fn=generate_caption,
    inputs=[gr.Image(type="pil", label="Upload Image"), gr.Textbox(label="Prompt", value="Describe the image in great detail")],
    outputs=gr.Textbox(label="Generated Caption"),
    description=description
)

# Launch the interface
demo.launch(share=True)



####### ML CODE #######
import torch
from PIL import Image
from transformers import AutoModelForCausalLM, AutoTokenizer

MODEL_PATH = "THUDM/cogvlm2-llama3-chat-19B"
DEVICE = 'cuda' if torch.cuda.is_available() else 'cpu'
TORCH_TYPE = torch.bfloat16 if torch.cuda.is_available() and torch.cuda.get_device_capability()[0] >= 8 else torch.float16

tokenizer = AutoTokenizer.from_pretrained(
    MODEL_PATH,
    trust_remote_code=True
)
model = AutoModelForCausalLM.from_pretrained(
    MODEL_PATH,
    torch_dtype=TORCH_TYPE,
    trust_remote_code=True,
).to(DEVICE).eval()

text_only_template = "A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: {} ASSISTANT:"

while True:
    image_path = input("image path >>>>> ")
    if image_path == '':
        print('You did not enter image path, the following will be a plain text conversation.')
        image = None
        text_only_first_query = True
    else:
        image = Image.open(image_path).convert('RGB')

    history = []

    while True:
        query = input("Human:")
        if query == "clear":
            break

        if image is None:
            if text_only_first_query:
                query = text_only_template.format(query)
                text_only_first_query = False
            else:
                old_prompt = ''
                for _, (old_query, response) in enumerate(history):
                    old_prompt += old_query + " " + response + "\n"
                query = old_prompt + "USER: {} ASSISTANT:".format(query)
        if image is None:
            input_by_model = model.build_conversation_input_ids(
                tokenizer,
                query=query,
                history=history,
                template_version='chat'
            )
        else:
            input_by_model = model.build_conversation_input_ids(
                tokenizer,
                query=query,
                history=history,
                images=[image],
                template_version='chat'
            )
        inputs = {
            'input_ids': input_by_model['input_ids'].unsqueeze(0).to(DEVICE),
            'token_type_ids': input_by_model['token_type_ids'].unsqueeze(0).to(DEVICE),
            'attention_mask': input_by_model['attention_mask'].unsqueeze(0).to(DEVICE),
            'images': [[input_by_model['images'][0].to(DEVICE).to(TORCH_TYPE)]] if image is not None else None,
        }
        gen_kwargs = {
            "max_new_tokens": 2048,
            "pad_token_id": 128002,  
        }
        with torch.no_grad():
            outputs = model.generate(**inputs, **gen_kwargs)
            outputs = outputs[:, inputs['input_ids'].shape[1]:]
            response = tokenizer.decode(outputs[0])
            response = response.split("<|end_of_text|>")[0]
            print("\nCogVLM2:", response)
        history.append((query, response))