File size: 3,423 Bytes
093bfef |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 |
import gradio as gr
import os
import litellm
DESCRIPTION = '''
<div>
<h1 style="text-align: center;">TAIDE/Llama-3.1-TAIDE-LX-8B-Chat</h1>
<p>This Space demonstrates the instruction-tuned model <a href="https://huggingface.co/taide/Llama-3.1-TAIDE-LX-8B-Chat"><b>Llama-3.1-TAIDE-LX-8B-Chat</b></a>. Llama-3.1-TAIDE-LX-8B-Chat is the new open LLM and comes in one sizes: 8b. Feel free to play with it, or duplicate to run privately!</p>
</div>
'''
LICENSE = """
<p/>
---
Built with Llama-3.1-TAIDE-LX-8B-Chat
"""
css = """
h1 {
text-align: center;
display: block;
}
#duplicate-button {
margin: auto;
color: white;
background: #1565c0;
border-radius: 100vh;
}
"""
def chat(message: str,
history: list,
temperature: float,
max_new_tokens: int
) -> str:
try:
messages = []
for user, assistant in history:
messages.extend([{"role": "user", "content": user}, {"role": "assistant", "content": assistant}])
messages.append({"role": "user", "content": message})
response = litellm.completion(
model="openai/Llama-3.1-TAIDE-LX-8B-Chat", # tells litellm to call the model via the Responses API
messages=messages,
max_completion_tokens=max_new_tokens,
temperature=temperature,
stream=True,
)
output = []
for part in response:
content = part.choices[0].delta.content or ""
output.append(content)
yield "".join(output)
except Exception as e:
yield f"生成過程中發生錯誤: {str(e)}"
# Gradio block
chatbot = gr.Chatbot(height=450, 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,
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=131584,
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(server_name='0.0.0.0')
|