app.py

import gradio as gr
import os
import spaces
from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
from threading import Thread

# Set an environment variable
HF_TOKEN = os.environ.get("HF_TOKEN", None)

DESCRIPTION = '''
<div>
<h1 style="text-align: center;">Mistral Chat</h1>
</div>
'''

LICENSE = """
<p/>
---
"""

PLACEHOLDER = """
<div style="padding: 30px; text-align: center; display: flex; flex-direction: column; align-items: center;">
   <h1 style="font-size: 28px; margin-bottom: 2px; opacity: 0.55;">DeepSeek-R1-Distill-Llama-8B</h1>
   <p style="font-size: 18px; margin-bottom: 2px; opacity: 0.65;">Ask me anything...</p>
</div>
"""

css = """
h1 {
  text-align: center;
  display: block;
}

#duplicate-button {
  margin: auto;
  color: white;
  background: #1565c0;
  border-radius: 100vh;
}
"""

# Load the tokenizer and model
tokenizer = AutoTokenizer.from_pretrained("mistralai/Ministral-8B-Instruct-2410")
model = AutoModelForCausalLM.from_pretrained("mistralai/Ministral-8B-Instruct-2410", device_map="auto")

terminators = [
    tokenizer.eos_token_id,
    tokenizer.convert_tokens_to_ids("<|eot_id|>")
]

@spaces.GPU(duration=120)
def chat_llama3_8b(message: str, 
                    history: list, 
                    temperature: float, 
                    max_new_tokens: int,
                    system_prompt: str) -> str:
    """
    Generate a streaming response using the Mistral-8B model.
    Args:
        message (str): The input message.
        history (list): The conversation history used by ChatInterface.
        temperature (float): The temperature for generating the response.
        max_new_tokens (int): The maximum number of new tokens to generate.
        system_prompt (str): The system prompt to guide the assistant's behavior.
    Returns:
        str: The generated response.
    """
    conversation = []

    # Include system prompt at the beginning if provided
    if system_prompt:
        conversation.append({"role": "system", "content": system_prompt})

    for user, assistant in history:
        conversation.extend([{"role": "user", "content": user}, {"role": "assistant", "content": assistant}])
    
    conversation.append({"role": "user", "content": message})

    input_ids = tokenizer.apply_chat_template(conversation, return_tensors="pt").to(model.device)
    
    streamer = TextIteratorStreamer(tokenizer, timeout=10.0, skip_prompt=True, skip_special_tokens=True)

    generate_kwargs = dict(
        input_ids=input_ids,
        streamer=streamer,
        max_new_tokens=max_new_tokens,
        do_sample=True,
        temperature=temperature,
        eos_token_id=terminators,
    )

    if temperature == 0:
        generate_kwargs['do_sample'] = False
        
    t = Thread(target=model.generate, kwargs=generate_kwargs)
    t.start()

    outputs = []
    for text in streamer:
        outputs.append(text)
        yield "".join(outputs)
        

# Gradio block
chatbot = gr.Chatbot(height=450, placeholder=PLACEHOLDER, label='Gradio ChatInterface')

with gr.Blocks(fill_height=True, css=css) as demo:
    
    gr.Markdown(DESCRIPTION)

    system_prompt_input = gr.Textbox(
        label="System Prompt",
        placeholder="Enter system instructions for the model...",
        lines=2
    )

    gr.ChatInterface(
        fn=chat_llama3_8b,
        chatbot=chatbot,
        fill_height=True,
        additional_inputs_accordion=gr.Accordion(label="⚙️ Parameters", open=False, render=False),
        additional_inputs=[
            system_prompt_input,
            gr.Slider(minimum=0, maximum=1, step=0.1, value=0.8, label="Temperature", render=False),
            gr.Slider(minimum=128, maximum=4096, step=1, value=4096, label="Max new tokens", render=False),
        ],
        examples=[
            ['Are you a sentient being?']
        ],
        cache_examples=False
    )

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