app.py

import gradio as gr
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
"""
new_path = "meta-llama/Meta-Llama-3.1-8B-Instruct" # cannot use 需pro用户
new_path2 = "Nexesenex/TeeZee_Kyllene-Yi-34B-v1.1-iMat.GGUF"
new_path1 = "tastypear/CausalLM-7B-DPO-alpha-GGUF" # cannot use
new_path3 = "aifeifei798/llama3-8B-DarkIdol-2.3-Uncensored-32K"
new_path4 = "marianna13/byt5-small-NSFW-image-urls"
origin_path = "HuggingFaceH4/zephyr-7b-beta"
funny_path = "cognitivecomputations/WizardLM-7B-Uncensored"
funny_model = "AI-B/UTENA-7B-NSFW-V2"
translate_model = "utrobinmv/t5_translate_en_ru_zh_small_1024"
client = InferenceClient(translate_model)


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

"""
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)",
        ),
    ],
)


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