import gradio as gr from huggingface_hub import InferenceClient client = InferenceClient("HuggingFaceH4/zephyr-7b-beta") def respond(message, history, system_message, max_tokens, temperature, top_p): messages = [{"role": "system", "content": system_message}] for user, assistant in history: if user: messages.append({"role": "user", "content": user}) if assistant: messages.append({"role": "assistant", "content": assistant}) 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 # Custom CSS for improved visual appeal custom_css = """ body { background-color: #f0f4f8; font-family: 'Arial', sans-serif; } .gradio-container { max-width: 800px !important; margin: auto; padding: 20px; border-radius: 15px; box-shadow: 0 4px 6px rgba(0, 0, 0, 0.1); background-color: white; } .chat-window { border-radius: 10px; border: 1px solid #e0e0e0; } .chat-message { padding: 10px 15px; border-radius: 8px; margin: 5px 0; } .user-message { background-color: #e3f2fd; } .bot-message { background-color: #f1f8e9; } """ # Create the ChatInterface with custom styling demo = gr.ChatInterface( respond, additional_inputs=[ gr.Textbox(value="You are a friendly Chatbot.", label="System Message", lines=2), 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)"), ], title="Enhanced AI Chatbot", description="Engage in a conversation with an AI powered by the Zephyr-7b-beta model.", theme="soft", css=custom_css, examples=[ ["Tell me a short story about a robot learning to paint."], ["What are the main challenges in space exploration?"], ["Explain quantum computing to a 10-year-old."] ], ) if __name__ == "__main__": demo.launch()