import gradio as gr from huggingface_hub import InferenceClient client = InferenceClient("BenBranyon/zephyr-sumbot-all-songs") def respond( message, history: list[tuple[str, str]], max_tokens, temperature, top_p, ): messages = [{"role": "system", "content": "You are a rap lyric generation bot representing the imagination of the artist Sumkilla. Try to avoid words that would offend anyone. Try to rhyme as much as possible."}] 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": "Write a rap about " + 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 demo = gr.ChatInterface( respond, chatbot=gr.Chatbot(placeholder="Sumbot
Hello human. What would you like me to rap about today?"), retry_btn=None, textbox=gr.Textbox(placeholder="Subject of the song", container=False, scale=7), css="styles.css", additional_inputs=[ gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"), gr.Slider(minimum=0.1, maximum=4.0, value=0.6, step=0.1, label="Temperature"), gr.Slider( minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)", ), ], ) if __name__ == "__main__": demo.launch()