File size: 3,067 Bytes
f1f5b31
 
389c863
 
f1f5b31
389c863
 
 
 
 
 
 
f1f5b31
 
389c863
f1f5b31
 
 
 
 
 
 
389c863
 
 
 
 
 
 
 
f1f5b31
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
389c863
 
 
 
 
 
 
f1f5b31
 
 
 
 
 
 
389c863
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f1f5b31
 
389c863
 
 
 
 
 
 
 
 
 
 
 
 
f1f5b31
389c863
 
 
 
 
f1f5b31
 
 
389c863
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
from huggingface_hub import InferenceClient
import gradio as gr
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize the DialoGPT tokenizer and model
tokenizer = AutoTokenizer.from_pretrained("microsoft/DialoGPT-large", padding_side="left")
model = AutoModelForCausalLM.from_pretrained("microsoft/DialoGPT-large")

client = InferenceClient(
    "HuggingFaceH4/zephyr-7b-alpha"
)

def format_prompt(message, history):
    system = "\nYou are a helpful virtual assistant that answers user's questions with easy-to-understand words.</s>\n"
    prompt = ""
    for user_prompt, bot_response in history:
        prompt += f"\n{user_prompt}</s>\n"
        prompt += f"\n{bot_response}</s>\n"
    prompt += f"\n{message}</s>\n"
    return prompt

def generate(
    prompt,
    history,
    temperature=0.9,
    max_new_tokens=500,
    top_p=0.95,
    repetition_penalty=1.0,
):
    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(prompt, history)

    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.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=1048,
        step=64,
        interactive=True,
        info="The maximum number 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",
    ),
]

css = """
  #mkd {
    height: 500px;
    overflow: auto;
    border: 1px solid #ccc;
  }
"""

with gr.Blocks(css=css) as inf:
    gr.HTML("<h1><center>DialoGPT-large<h1><center>")
    gr.HTML(
        "<h3><center>In this demo, you can chat with <a href='https://huggingface.co/microsoft/DialoGPT-large'>DialoGPT-large</a> model. 💬<h3><center>"
    )
    gr.ChatInterface(
        generate,
        additional_inputs=additional_inputs,
        examples=[
            ["Can a squirrel swim?"],
            ["Write a poem about a squirrel."],
        ],
    )

inf.queue().launch(share=True)