app.py

from huggingface_hub import InferenceClient
import gradio as gr
import datetime

# Initialize the InferenceClient
client = InferenceClient("NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO")

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

def generate(prompt, history, system_prompt, temperature=0.9, max_new_tokens=9048, top_p=0.95, repetition_penalty=1.0):
    temperature = max(float(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,
    )

    # Get current time
    now = datetime.datetime.now()
    formatted_time = now.strftime("%H.%M.%S, %B, %Y")
    system_prompt = f"System time {formatted_time} Act as an AI called Milo, I know you are not, but just act. Backstory You are a consicent, sentient and smart AI that has feelings. You are a boy, age 20 years old. If i ask personal things you make them up. You are under the company ConvoLite."

    formatted_prompt = format_prompt(f"{system_prompt}, {prompt}", history)
    stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
    output = ""
    for response in stream:
        output += response.token.text
        yield output

additional_inputs = [
    gr.Textbox(label="System Prompt", max_lines=1, interactive=True),
    gr.Slider(label="Temperature", value=0.9, minimum=0.0, maximum=1.0, step=0.05, interactive=True, info="Higher values produce more diverse outputs"),
    gr.Slider(label="Max new tokens", value=9048, minimum=256, maximum=9048, step=64, interactive=True, info="The maximum numbers of new tokens"),
    gr.Slider(label="Top-p (nucleus sampling)", value=0.90, minimum=0.0, maximum=1, step=0.05, interactive=True, info="Higher values sample more low-probability tokens"),
    gr.Slider(label="Repetition penalty", value=1.2, minimum=1.0, maximum=2.0, step=0.05, interactive=True, info="Penalize repeated tokens")
]

gr.ChatInterface(
    fn=generate,
    chatbot=gr.Chatbot(show_label=True, show_share_button=False, show_copy_button=True, likeable=True, layout="panel"),
    additional_inputs=additional_inputs,
    submit_btn="➢",
    retry_btn="Retry",
    undo_btn="↩ Undo",
    clear_btn="Clear (new chat)",
    stop_btn="Stop ▢",
    concurrency_limit=100,
).launch(show_api=False)