app.py

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

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

zero = torch.Tensor([0]).cuda()
print(zero.device) # <-- 'cpu' 🤔

LICENSE = """
<p/>
---
Built with Meta Llama 3
"""

# Load the tokenizer and model
tokenizer = AutoTokenizer.from_pretrained("taide/Llama3-TAIDE-LX-8B-Chat-Alpha1")
model = AutoModelForCausalLM.from_pretrained("taide/Llama3-TAIDE-LX-8B-Chat-Alpha1")  # to("cuda:0") 
terminators = [
    tokenizer.eos_token_id,
    tokenizer.convert_tokens_to_ids("<|eot_id|>")
]

@spaces.GPU(duration=120)
def chat_taide_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").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.DuplicateButton(value="Duplicate Space for private use", elem_id="duplicate-button")
    gr.ChatInterface(
        fn=chat_taide_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=[
            ['請以以下內容為基礎，寫一篇文章：撰寫一篇作文，題目為《一張舊照片》，內容要求為：選擇一張令你印象深刻的照片，說明令你印象深刻的原因，並描述照片中的影像及背後的故事。記錄成長的過程、與他人的情景、環境變遷和美麗的景色。'],
            ['請以品牌經理的身份，給廣告公司的創意總監寫一封信，提出對於新產品廣告宣傳活動的創意建議。'],
            ['以下提供英文內容，請幫我翻譯成中文。Dongshan coffee is famous for its unique position, and the constant refinement of production methods. The flavor is admired by many caffeine afficionados.'],
            ],
        cache_examples=False,
                     )
    
    gr.Markdown(LICENSE)
    
if __name__ == "__main__":
    demo.launch()