app.py

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

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


DESCRIPTION = """
<div>
<h1 style="text-align: center;">SPUM Table Extraction</h1>
<p>This Space demonstrates the instruction-tuned model <a href="https://huggingface.co/khulaifi95/Llama-3.1-8B-Reason-Blend-888k"><b>Meta Llama3 8b Chat</b></a>. Meta Llama3 is the new open LLM and comes in two sizes: 8b and 70b. Feel free to play with it, or duplicate to run privately!</p>
</div>
"""

PLACEHOLDER = """
<div style="padding: 30px; text-align: center; display: flex; flex-direction: column; align-items: center;">
   <img src="https://ysharma-dummy-chat-app.hf.space/file=/tmp/gradio/8e75e61cc9bab22b7ce3dec85ab0e6db1da5d107/Meta_lockup_positive%20primary_RGB.jpg" style="width: 80%; max-width: 550px; height: auto; opacity: 0.55;  "> 
   <h1 style="font-size: 28px; margin-bottom: 2px; opacity: 0.55;">Materials GPT</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
model_id = "khulaifi95/Llama-3.1-8B-Reason-Blend-888k"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")
terminators = [tokenizer.eos_token_id, tokenizer.convert_tokens_to_ids("<|eot_id|>")]


@spaces.GPU
def chat_llama3_8b(
    message: str, history: list, temperature: float, max_new_tokens: int
) -> Generator[str, None, None]:
    """
    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").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,
    )
    # This will enforce greedy generation (do_sample=False) when the temperature is passed 0, avoiding the crash.
    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)
        # print(outputs)
        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)
    gr.ChatInterface(
        fn=chat_llama3_8b,
        chatbot=chatbot,
        fill_height=True,
        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=[
            ["The detonative temperature of this polypropylene is 2000°F."],
            ["The preparation method according to claim 1, characterized in that the SO2 accounts for 30 wt% and the Fe2O3 accounts for 70 wt%."],
        ],
        cache_examples=False,
    )


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