import gradio as gr from huggingface_hub import InferenceClient # Markdown description DESCRIPTION = '''

zephyr-7b-beta

This Space demonstrates the instruction-tuned model zephyr-7b-beta by Hugging face. zephyr-7b-beta is the new open 7B parameter GPT-like model fine-tuned on a mix of publicly available, synthetic datasets.
It can work as a summarizer, sentiment analyzer and Q/A chatbot with multiple other facilities.
Feel free to play with it, or duplicate to run privately!

''' # License markdown LICENSE = """

--- Built with zephyr-7b-beta """ # Placeholder HTML PLACEHOLDER = """

zephyr-7b-beta

Ask me anything...

""" # 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(fill_height=True,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( fill_height=True, 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.'] ], cache_examples=False, additional_inputs_accordion = gr.Accordion(label="⚙️ Parameters", open=False, render= False), additional_inputs = [ gr.Textbox(value="You are a friendly Chatbot.", label="System message",render= False), gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens",render= False), gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature",render= False), gr.Slider( minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)", render= False ), ] ) # Add license markdown gr.Markdown(LICENSE) # Launch the interface if __name__ == "__main__": demo.launch(share=True)