File size: 3,588 Bytes
cd650c7
 
fceacf5
 
cd650c7
923f75f
 
 
 
cd650c7
fceacf5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cd650c7
923f75f
 
 
cd650c7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
43561b8
923f75f
fceacf5
 
 
 
 
 
923f75f
cd650c7
 
 
 
 
 
 
 
 
923f75f
 
 
 
 
fceacf5
 
 
 
 
923f75f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cd650c7
 
 
 
923f75f
43561b8
923f75f
 
 
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
from huggingface_hub import InferenceClient
import gradio as gr
import re
from nltk.tokenize import sent_tokenize

client = InferenceClient(
    "mistralai/Mixtral-8x7B-Instruct-v0.1"
)

def format_prompt(message, history):
    prompt = "<s>"
    for user_prompt, bot_response in history:
        prompt += f"[INST] {user_prompt} [/INST]"
        prompt += f" {bot_response}</s> "
    prompt += f"[INST] {message} [/INST]"
    return prompt

def tokenize_sentences(file_content):
    sentences = sent_tokenize(file_content.decode())
    return sentences

def generate_synthetic_data(prompt, sentences):
    synthetic_data = []
    for sentence in sentences:
        # Apply the prompt instructions to generate synthetic data from the sentence
        synthetic_sentence = f"{prompt}: {sentence}"
        synthetic_data.append(synthetic_sentence)
    return "\n".join(synthetic_data)

def generate(
    prompt, history, system_prompt, temperature=0.9, max_new_tokens=256, top_p=0.95, repetition_penalty=1.0, files=None
):
    temperature = float(temperature)
    if temperature < 1e-2:
        temperature = 1e-2
    top_p = float(top_p)

    generate_kwargs = dict(
        temperature=temperature,
        max_new_tokens=max_new_tokens,
        top_p=top_p,
        repetition_penalty=repetition_penalty,
        do_sample=True,
        seed=42,
    )

    formatted_prompt = format_prompt(f"{system_prompt}, {prompt}", history)

    if files is not None:
        file_contents = [file.decode() for file in files]
        sentences = []
        for content in file_contents:
            sentences.extend(tokenize_sentences(content))
        synthetic_data = generate_synthetic_data(prompt, sentences)
        formatted_prompt += f"\n\nSynthetic data: {synthetic_data}"

    stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
    output = ""

    for response in stream:
        output += response.token.text
        yield output
    return output

additional_inputs=[
    gr.Textbox(
        label="System Prompt",
        max_lines=1,
        interactive=True,
    ),
    gr.Textbox(
        label="Prompt for Synthetic Data Generation",
        max_lines=1,
        interactive=True,
    ),
    gr.Slider(
        label="Temperature",
        value=0.9,
        minimum=0.0,
        maximum=1.0,
        step=0.05,
        interactive=True,
        info="Higher values produce more diverse outputs",
    ),
    gr.Slider(
        label="Max new tokens",
        value=256,
        minimum=0,
        maximum=5120,
        step=64,
        interactive=True,
        info="The maximum numbers of new tokens",
    ),
    gr.Slider(
        label="Top-p (nucleus sampling)",
        value=0.90,
        minimum=0.0,
        maximum=1,
        step=0.05,
        interactive=True,
        info="Higher values sample more low-probability tokens",
    ),
    gr.Slider(
        label="Repetition penalty",
        value=1.2,
        minimum=1.0,
        maximum=2.0,
        step=0.05,
        interactive=True,
        info="Penalize repeated tokens",
    ),
    gr.File(
        label="Upload PDF or Document",
        file_count="multiple",
        file_types=[".pdf", ".doc", ".docx", ".txt"],
        interactive=True,
    )
]

gr.ChatInterface(
    fn=generate,
    chatbot=gr.Chatbot(show_label=False, show_share_button=False, show_copy_button=True, likeable=True, layout="panel"),
    additional_inputs=additional_inputs,
    title="Synthetic-data-generation-aze",
    concurrency_limit=20,
).launch(show_api=False)