app.py

from huggingface_hub import InferenceClient
import gradio as gr
client = InferenceClient("mistralai/Mixtral-8x7B-Instruct-v0.1")

def format_prompt(message, history, system_prompt):
    prompt = "<s>"
    for user_prompt, bot_response in history:
        prompt += f"[INST] {user_prompt} [/INST]"
        prompt += f" {bot_response}</s> "
    prompt += f"[INST] {message} [/INST]"
    prompt += f" [SYSTEM] {system_prompt} [/SYSTEM]"
    return prompt

def generate(
    prompt, history, system_prompt, temperature=0.2, max_new_tokens=256, top_p=0.95, repetition_penalty=1.0,
):
    temperature = float(temperature)
    if temperature < 1e-2:
        temperature = 1e-2
    top_p = float(top_p)
    generate_kwargs = dict(
        temperature=temperature,
        max_new_tokens=max_new_tokens,
        top_p=top_p,
        repetition_penalty=repetition_penalty,
        do_sample=True,
        seed=42,
    )
    formatted_prompt = format_prompt(prompt, history, system_prompt)
    stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
    output = ""
    for response in stream:
        output += response['text']
        yield output
    return output

mychatbot = gr.Chatbot(
    avatar_images=["./user.png", "./botm.png"],
    bubble_full_width=False,
    show_label=False,
    show_copy_button=True,
    likeable=True,
)

demo = gr.Interface(fn=generate, 
                    inputs=[gr.inputs.Textbox(lines=2, label="Your Message"), "state", "state"],
                    outputs=[gr.outputs.Textbox(label="ChatGPT's Response"), "state", "state"],
                    title="Tomoniai's Mixtral 8x7b Chat",
                    allow_flagging="never"
                   )
demo.launch(show_api=False)