app.py

# Ref: https://huggingface.co/spaces/ysharma/Chat_with_Meta_llama3_8b

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


DESCRIPTION = '''
<div>
<h1 style="text-align: center;">非公式Llama-3.1-Swallow-8B-Instruct-v0.1</h1>
<p>tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.1の非公式デモだよ。 <a href="https://huggingface.co/tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.1"><b>tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.1</b></a>.</p>
</div>
'''

LICENSE = """
<p/>

---
Built with Meta Llama 3.1
"""

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;">Meta llama3.1</h1>
   <p style="font-size: 18px; margin-bottom: 2px; opacity: 0.65;">なんでもきいてね</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("tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.1")
model = AutoModelForCausalLM.from_pretrained("tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.1", torch_dtype=torch.bfloat16, device_map="auto")

@spaces.GPU()
def chat_llama3_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 = []
    conversation.append({"role": "system", "content": "あなたは誠実で優秀な日本人のアシスタントです。日本語で聞かれた場合、必ず日本語で返答してください。"})
    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, tokenize=True, add_generation_prompt=True, 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,
        top_p=0.9,
        repetition_penalty=1.1,
    )
    # 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.DuplicateButton(value="Duplicate Space for private use", elem_id="duplicate-button")
    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=0.6, 
                      label="Temperature", 
                      render=False),
            gr.Slider(minimum=128, 
                      maximum=4096,
                      step=1,
                      value=1024, 
                      label="Max new tokens", 
                      render=False ),
            ],
        examples=[
            ['小学生にもわかるように相対性理論を教えてください。'],
            ['宇宙の起源を知るための方法をステップ・バイ・ステップで教えてください。'],
            ['1から100までの素数を求めるスクリプトをPythonで書いてください。'],
            ['友達の陽葵にあげる誕生日プレゼントを考えてください。ただし、陽葵は中学生で、私は同じクラスの男性であることを考慮してください。'],
            ['ペンギンがジャングルの王様であることを正当化するように説明してください。']
            ],
        cache_examples=False,
                     )
    
    gr.Markdown(LICENSE)
    
if __name__ == "__main__":
    demo.launch()