app.py

import gradio as gr
import spaces
from huggingface_hub import InferenceClient

"""
For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
"""
client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")


@spaces.GPU
def respond(
    message,
    task_type,
    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 = []
    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


"""
For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
"""
# demo = gr.ChatInterface(
#     respond,
#     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)",
#         ),
#     ],
# )
task_types = [
    "extractive question answering",
    "multiple-choice question answering",
    "question generation",
    "question answering without choices",
    "yes-no question answering",
    "coreference resolution",
    "paraphrase generation",
    "paraphrase identification",
    "sentence completion",
    "sentiment",
    "summarization",
    "text generation",
    "topic classification",
    "word sense disambiguation",
    "textual entailment",
    "natural language inference",
]

demo = gr.Interface(
    fn=respond,
    inputs=[
        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
        gr.Dropdown(task_types, label="Task type"),
    ],
    outputs=gr.Textbox(label="Response"),
    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=0.7, 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="Zephyr Chatbot",
    description="A chatbot that uses the Hugging Face Zephyr model.",
)


if __name__ == "__main__":
    demo.launch()