Lycor/HRM-Text

1import gradio as gr2from huggingface_hub import InferenceClient3 4 5def respond(6    message,7    history: list[dict[str, str]],8    system_message,9    max_tokens,10    temperature,11    top_p,12    hf_token: gr.OAuthToken,13):14    """15    For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference16    """17    client = InferenceClient(token=hf_token.token, model="openai/gpt-oss-20b")18 19    messages = [{"role": "system", "content": system_message}]20 21    messages.extend(history)22 23    messages.append({"role": "user", "content": message})24 25    response = ""26 27    for message in client.chat_completion(28        messages,29        max_tokens=max_tokens,30        stream=True,31        temperature=temperature,32        top_p=top_p,33    ):34        choices = message.choices35        token = ""36        if len(choices) and choices[0].delta.content:37            token = choices[0].delta.content38 39        response += token40        yield response41 42 43"""44For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface45"""46chatbot = gr.ChatInterface(47    respond,48    additional_inputs=[49        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),50        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),51        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),52        gr.Slider(53            minimum=0.1,54            maximum=1.0,55            value=0.95,56            step=0.05,57            label="Top-p (nucleus sampling)",58        ),59    ],60)61 62with gr.Blocks() as demo:63    with gr.Sidebar():64        gr.LoginButton()65    chatbot.render()66 67 68if __name__ == "__main__":69    demo.launch()70