app.py

import gradio as gr
from huggingface_hub import InferenceClient

# Markdown description
DESCRIPTION = '''
<div>
<h1 style="text-align: center;">zephyr-7b-beta</h1>
<p>This Space demonstrates the instruction-tuned model<b>zephyr-7b-beta by Hugging face</b></a>. zephyr-7b-beta is the new open 7B parameter GPT-like model fine-tuned on a mix of publicly available, synthetic datasets. Feel free to play with it, or duplicate to run privately!</p>
</div>
'''

# License markdown
LICENSE = """
<p/>
---
Built with zephyr-7b-beta
"""

# Placeholder HTML
PLACEHOLDER = """
<div style="padding: 30px; text-align: center; display: flex; flex-direction: column; align-items: center;">
   <img src="https://ysharma-dummy-chat-app.hf.space/file=/tmp/gradio/8e75e61cc9bab22b7ce3dec85ab0e6db1da5d107/Meta_lockup_positive%20primary_RGB.jpg" style="width: 80%; max-width: 550px; height: auto; opacity: 0.55;  "> 
   <h1 style="font-size: 28px; margin-bottom: 2px; opacity: 0.55;">zephyr-7b-beta</h1>
   <p style="font-size: 18px; margin-bottom: 2px; opacity: 0.65;">Ask me anything...</p>
</div>
"""

# CSS styles
css = """
h1 {
  text-align: center;
  display: block;
}
#duplicate-button {
  margin: auto;
  color: white;
  background: #1565c0;
  border-radius: 100vh;
}
"""

# Initialize InferenceClient
client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")

# Function to respond to user messages
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

# Create a Chatbot
chatbot=gr.Chatbot(height=450, placeholder=PLACEHOLDER, label='Gradio ChatInterface')

# Define the interface layout
with gr.Blocks(css=css) as demo:
    # Add description markdown
    gr.Markdown(DESCRIPTION)
    # Add duplicate button
    gr.DuplicateButton(value="Duplicate Space for private use", elem_id="duplicate-button")
    # Add chat interface
    gr.ChatInterface(
        fn=respond,
        chatbot=chatbot,
        examples=[
            ['How to setup a human base on Mars? Give short answer.'],
            ['Explain theory of relativity to me like I’m 8 years old.'],
            ['What is 9,000 * 9,000?'],
            ['Write a pun-filled happy birthday message to my friend Alex.'],
            ['Justify why a penguin might make a good king of the jungle.']
        ],
        additional_inputs_accordion=gr.Accordion(label="⚙️ Parameters", open=False, render=False),
        additional_inputs=[
            gr.Textbox(value="You are a friendly Chatbot.", 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)",
            ),
        ],
        cache_examples=False,
    )
        # Add license markdown
    gr.Markdown(LICENSE)

# Launch the interface
if __name__ == "__main__":
    demo.launch()