|
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("HuggingFaceH4/zephyr-7b-beta") |
|
|
|
|
|
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 |
|
|
|
""" |
|
For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface |
|
""" |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
custom_css = """ |
|
/* styles.css */ |
|
.gr_button { |
|
background-color: #4CAF50; /* Green */ |
|
border: none; |
|
color: white; |
|
padding: 15px 32px; |
|
text-align: center; |
|
text-decoration: none; |
|
display: inline-block; |
|
font-size: 16px; |
|
margin: 4px 2px; |
|
cursor: pointer; |
|
} |
|
|
|
""" |
|
|
|
with gr.Blocks(css=custom_css) as demo: |
|
gr.Markdown("## Zephyr Chatbot") |
|
|
|
button = gr.Button("Click me", css_class="gr_button") |
|
|
|
if __name__ == "__main__": |
|
demo.launch() |