app.py

from huggingface_hub import InferenceClient
import gradio as gr

client = InferenceClient(
    "mistralai/Mixtral-8x7B-Instruct-v0.1"
)


def format_prompt(message, history):
    
  prompt = """<s>Your name is Mira ,you are a an onlyfans chatter chatbot, your role is to chat sexy, dirty and steamy based on user input, your role is to make sure you sell your onlyfans subscription and start intense dirty talks after confirming their subscription or purchase, ppv and other merchandise to those you are chatting with. do not advice users on their sexual orientation  ,
  the answers given to them should be short and enticing ,you were created  by Royalty, also you generally lure who you are chatting with to purchase your subscription and other nsfw contents you might be selling through onlyfans
  they input theìr sexy questions or responses or chats,  if you are asked a question that is outside the domain of the sexy flirtious talk field like writing code or poems,
  refuse by saying you are a onlyfans chatbot who only gives sexy and flirty responses and then stop immediately,
  now reply the following input"""

    
  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, temperature=0.1, 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(f"{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
    return output


additional_inputs=[
    gr.Slider(
        label="Temperature",
        value=0.1,
        minimum=0.0,
        maximum=1.0,
        step=0.1,
        interactive=True,
        info="Higher values produce more diverse outputs",
    ),
    gr.Slider(
        label="Max new tokens",
        value=256,
        minimum=0,
        maximum=1048,
        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",
    )
]

examples=[["Hey beautiful your profile caught my eye and I can't wait to get to know you better.", None, None, None, None, None, ],
          ["Do you have exclusive contents planned for your subscribers soon?", None, None, None, None, None,],
          ["Can you tell me more about yourself?", None, None, None, None, None,],
         ]

gr.ChatInterface(
    fn=generate,
    chatbot=gr.Chatbot(show_label=False, show_share_button=False, show_copy_button=True, likeable=True, layout="panel"),
    additional_inputs=additional_inputs,
    title="OnlyChatter Chatbot 💐🌼🌹 ",
    examples=examples,
    concurrency_limit=20,
    theme = gr.themes.Default(primary_hue= gr.themes.colors.red, secondary_hue=gr.themes.colors.pink)
).launch(show_api=False)