File size: 3,170 Bytes
c3dfc09 334df3e 0802b34 8d3c493 c3dfc09 8d3c493 1ee4bc1 334df3e e1f2405 89224bc 51ab81f 334df3e 51ab81f c3dfc09 334df3e dc0ecdd c3dfc09 dc0ecdd c3dfc09 51ab81f c3dfc09 8d3c493 c3dfc09 1ee4bc1 |
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 |
import gradio as gr
from huggingface_hub import InferenceClient
"""
For more information on huggingface_hub Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
"""
client = InferenceClient("Qwen/QwQ-32B")
def respond(
message,
history: list[tuple[str, str]],
system_message,
max_tokens,
temperature,
top_p,
):
messages = [{"role": "system", "content": system_message}]
for val in history:
if val[0]:
messages.append({"role": "user", "content": val[0]})
if val[1]:
messages.append({"role": "assistant", "content": val[1]})
messages.append({"role": "user", "content": message})
response = ""
for message in client.chat_completion(
messages,
max_tokens=max_tokens,
stream=True,
temperature=temperature,
top_p=top_p,
):
token = message.choices[0].delta.content
response += token
yield response
# Define custom CSS for Flat Design
flat_design_css = """
* {
margin: 0;
padding: 0;
box-sizing: border-box;
font-family: 'Helvetica', sans-serif;
}
.gradio-container {
background-color: #f4f4f9;
padding: 20px;
border-radius: 8px;
}
.gradio-button {
background-color: #4CAF50;
color: white;
border: none;
border-radius: 5px;
padding: 10px 20px;
font-size: 16px;
cursor: pointer;
transition: background-color 0.3s ease;
}
.gradio-button:hover {
background-color: #45a049;
}
.gradio-slider {
background-color: #e1e1e1;
border-radius: 8px;
}
.gradio-textbox {
background-color: #ffffff;
border: 1px solid #ddd;
border-radius: 8px;
padding: 10px;
font-size: 14px;
width: 100%;
transition: border-color 0.3s ease;
}
.gradio-textbox:focus {
border-color: #4CAF50;
}
.gradio-label {
font-size: 14px;
font-weight: bold;
color: #333;
}
.gradio-interface .gradio-input-container {
margin-bottom: 20px;
}
"""
# Launch the Gradio app with custom CSS
demo = gr.ChatInterface(
respond,
additional_inputs=[
gr.Textbox(value="Здравствуйте. Отвечай кратко(не пиши вступление, умозаключения итп) и сразу пиши начинай с этого ответ: Предварительный диагноз:(диагноз), Операция: (Если требуется, только название), Лечение: (Кратко, очень). Не пиши воду. Только по факту на 3 пункта отвечай. Не отходи от этого шаблона", label="System message"),
gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
gr.Slider(
minimum=0.1,
maximum=1.0,
value=0.95,
step=0.05,
label="Top-p (nucleus sampling)",
),
],
css=flat_design_css, # Applying the custom CSS
)
if __name__ == "__main__":
demo.launch()
|