app.py

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

TITLE = ''

DESCRIPTION = ''

LICENSE = """
<p>Built with Llama</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: 0.85;">Gameapp</h1>
   <p style="font-size: 18px; margin-bottom: 2px; opacity: 0.75;">Ask me anything...</p>
</div>
"""

css = """
h1 {
  text-align: center;
  display: block;
  display: flex;
  align-items: center;
  justify-content: center;
}

.gradio-container {
  border: 1px solid #ddd;
  border-radius: 10px;
  padding: 20px;
  box-shadow: 0 4px 8px rgba(0,0,0,0.1);
}

.gradio-chatbot .input-container {
  border-top: 1px solid #ddd;
  padding-top: 10px;
}

.gradio-chatbot .input-container textarea {
  border: 1px solid #ddd;
  border-radius: 5px;
  padding: 10px;
  width: 100%;
  box-sizing: border-box;
  resize: none;
  height: 50px;
}

.gradio-chatbot .message {
  border-radius: 10px;
  padding: 10px;
  margin: 10px 0;
  box-shadow: 0 4px 8px rgba(0,0,0,0.1);
}

.gradio-chatbot .message.user {
  background-color: #f5f5f5;
}

.gradio-chatbot .message.assistant {
  background-color: #e6f7ff;
}
"""

model_id = "abhillubillu/gameapp_model"
hf_token = os.getenv("HF_API_TOKEN")

# Load the tokenizer and model
tokenizer = AutoTokenizer.from_pretrained(model_id, token=hf_token)
model = AutoModelForCausalLM.from_pretrained(model_id, token=hf_token, device_map="auto")

# Ensure eos_token_id is set
eos_token_id = tokenizer.eos_token_id
if eos_token_id is None:
    eos_token_id = tokenizer.pad_token_id

terminators = [
    eos_token_id,
    tokenizer.convert_tokens_to_ids("")
]

MAX_INPUT_TOKEN_LENGTH = 4096

# Gradio inference function
@spaces.GPU(duration=120)
def chat_llama3_1_8b(message: str, 
              history: list, 
              temperature: float, 
              max_new_tokens: int
             ) -> str:
    """
    Generate a streaming response using the llama3-8b 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.
    Returns:
        str: The generated response.
    """
    conversation = []
    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")
    if input_ids.shape[1] > MAX_INPUT_TOKEN_LENGTH:
        input_ids = input_ids[:, -MAX_INPUT_TOKEN_LENGTH:]
        gr.Warning(f"Trimmed input from conversation as it was longer than {MAX_INPUT_TOKEN_LENGTH} tokens.")
    input_ids = input_ids.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=temperature != 0,  # This will enforce greedy generation (do_sample=False) when the temperature is passed 0, avoiding the crash.
        temperature=temperature,
        eos_token_id=terminators,
    )

    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(TITLE)
    gr.Markdown(DESCRIPTION)
    gr.ChatInterface(
        fn=chat_llama3_1_8b,
        chatbot=chatbot,
        fill_height=True,
        examples_per_page=3,
        additional_inputs_accordion=gr.Accordion(label="⚙️ Parameters", open=False, render=False),
        additional_inputs=[
            gr.Slider(minimum=0,
                      maximum=1, 
                      step=0.1,
                      value=0.95, 
                      label="Temperature", 
                      render=False),
            gr.Slider(minimum=128, 
                      maximum=4096,
                      step=1,
                      value=512, 
                      label="Max new tokens", 
                      render=False ),
            ],
        examples=[
            ["There's a llama in my garden 😱 What should I do?"],
            ["What is the best way to open a can of worms?"],
            ["The odd numbers in this group add up to an even number: 15, 32, 5, 13, 82, 7, 1. "],
            ['How to setup a human base on Mars? Give short answer.'],
            ['Explain theory of relativity to me like I’m 8 years old.'],
            ['What is 9,000 * 9,000?'],
            ['Write a pun-filled happy birthday message to my friend Alex.'],
            ['Justify why a penguin might make a good king of the jungle.']
            ],
        cache_examples=False,
                     )
    
    gr.Markdown(LICENSE)
    
if __name__ == "__main__":
    demo.launch()