Spaces:
Paused
Paused
| from typing import Iterator | |
| import gradio as gr | |
| import torch | |
| from model import run | |
| DEFAULT_SYSTEM_PROMPT = "" | |
| MAX_MAX_NEW_TOKENS = 2048 | |
| DEFAULT_MAX_NEW_TOKENS = 1024 | |
| MAX_INPUT_TOKEN_LENGTH = 4000 | |
| DESCRIPTION = """ | |
| # Baichuan2-13B-Chat | |
| Baichuan 2 is the new generation of open-source large language models launched by Baichuan Intelligent Technology. It was trained on a high-quality corpus with 2.6 trillion tokens. | |
| """ | |
| LICENSE = "" | |
| if not torch.cuda.is_available(): | |
| DESCRIPTION += '\n<p>Running on CPU 🥶 This demo does not work on CPU.</p>' | |
| def clear_and_save_textbox(message: str) -> tuple[str, str]: | |
| return '', message | |
| def display_input( | |
| message: str, | |
| history: list[tuple[str, str]] | |
| ) -> list[tuple[str, str]]: | |
| history.append((message, '')) | |
| return history | |
| def delete_prev_fn( | |
| history: list[tuple[str, str]] | |
| ) -> tuple[list[tuple[str, str]], str]: | |
| try: | |
| message, _ = history.pop() | |
| except IndexError: | |
| message = '' | |
| return history, message or '' | |
| def generate( | |
| message: str, | |
| history_with_input: list[tuple[str, str]], | |
| max_new_tokens: int, | |
| temperature: float, | |
| top_p: float, | |
| top_k: int, | |
| ) -> Iterator[list[tuple[str, str]]]: | |
| if max_new_tokens > MAX_MAX_NEW_TOKENS: | |
| raise ValueError | |
| history = history_with_input[:-1] | |
| generator = run(message, history, max_new_tokens, temperature, top_p, top_k) | |
| for response in generator: | |
| yield history + [(message, response)] | |
| def process_example(message: str) -> tuple[str, list[tuple[str, str]]]: | |
| generator = generate(message, [], DEFAULT_MAX_NEW_TOKENS, 1, 0.95, 5) | |
| for x in generator: | |
| pass | |
| return '', x | |
| with gr.Blocks(css='style.css') as demo: | |
| gr.Markdown(DESCRIPTION) | |
| gr.DuplicateButton( | |
| value='Duplicate Space for private use', | |
| elem_id='duplicate-button' | |
| ) | |
| with gr.Group(): | |
| chatbot = gr.Chatbot(label='Chatbot') | |
| with gr.Row(): | |
| textbox = gr.Textbox( | |
| container=False, | |
| show_label=False, | |
| placeholder='Type a message...', | |
| scale=10, | |
| ) | |
| submit_button = gr.Button( | |
| 'Submit', | |
| variant='primary', | |
| scale=1, | |
| min_width=0 | |
| ) | |
| with gr.Row(): | |
| retry_button = gr.Button('🔄 Retry', variant='secondary') | |
| undo_button = gr.Button('↩️ Undo', variant='secondary') | |
| clear_button = gr.Button('🗑️ Clear', variant='secondary') | |
| saved_input = gr.State() | |
| with gr.Accordion(label='Advanced options', open=False): | |
| max_new_tokens = gr.Slider( | |
| label='Max new tokens', | |
| minimum=1, | |
| maximum=MAX_MAX_NEW_TOKENS, | |
| step=1, | |
| value=DEFAULT_MAX_NEW_TOKENS, | |
| ) | |
| temperature = gr.Slider( | |
| label='Temperature', | |
| minimum=0.1, | |
| maximum=4.0, | |
| step=0.1, | |
| value=1.0, | |
| ) | |
| top_p = gr.Slider( | |
| label='Top-p (nucleus sampling)', | |
| minimum=0.05, | |
| maximum=1.0, | |
| step=0.05, | |
| value=0.95, | |
| ) | |
| top_k = gr.Slider( | |
| label='Top-k', | |
| minimum=1, | |
| maximum=1000, | |
| step=1, | |
| value=5, | |
| ) | |
| gr.Examples( | |
| examples=[ | |
| '介绍下你自己', | |
| '找到下列数组的中位数[3.1,6.2,1.3,8.4,10.5,11.6,2.1],请用python代码完成以上功能', | |
| '鸡和兔在一个笼子里,共有26个头,68只脚,那么鸡有多少只,兔有多少只?', | |
| '以下物理常识题目,哪一个是错误的?A.在自然环境下,声音在固体中传播速度最快。B.牛顿第一定律:一个物体如果不受力作用,将保持静止或匀速直线运动的状态。C.牛顿第三定律:对于每个作用力,都有一个相等而反向的反作用力。D.声音在空气中的传播速度为1000m/s。', | |
| ], | |
| inputs=textbox, | |
| outputs=[textbox, chatbot], | |
| fn=process_example, | |
| cache_examples=True, | |
| ) | |
| gr.Markdown(LICENSE) | |
| textbox.submit( | |
| fn=clear_and_save_textbox, | |
| inputs=textbox, | |
| outputs=[textbox, saved_input], | |
| api_name=False, | |
| queue=False, | |
| ).then( | |
| fn=display_input, | |
| inputs=[saved_input, chatbot], | |
| outputs=chatbot, | |
| api_name=False, | |
| queue=False, | |
| ).then( | |
| fn=generate, | |
| inputs=[ | |
| saved_input, | |
| chatbot, | |
| max_new_tokens, | |
| temperature, | |
| top_p, | |
| top_k, | |
| ], | |
| outputs=chatbot, | |
| api_name=False, | |
| ) | |
| button_event_preprocess = submit_button.click( | |
| fn=clear_and_save_textbox, | |
| inputs=textbox, | |
| outputs=[textbox, saved_input], | |
| api_name=False, | |
| queue=False, | |
| ).then( | |
| fn=display_input, | |
| inputs=[saved_input, chatbot], | |
| outputs=chatbot, | |
| api_name=False, | |
| queue=False, | |
| ).then( | |
| fn=generate, | |
| inputs=[ | |
| saved_input, | |
| chatbot, | |
| max_new_tokens, | |
| temperature, | |
| top_p, | |
| top_k, | |
| ], | |
| outputs=chatbot, | |
| api_name=False, | |
| ) | |
| retry_button.click( | |
| fn=delete_prev_fn, | |
| inputs=chatbot, | |
| outputs=[chatbot, saved_input], | |
| api_name=False, | |
| queue=False, | |
| ).then( | |
| fn=display_input, | |
| inputs=[saved_input, chatbot], | |
| outputs=chatbot, | |
| api_name=False, | |
| queue=False, | |
| ).then( | |
| fn=generate, | |
| inputs=[ | |
| saved_input, | |
| chatbot, | |
| max_new_tokens, | |
| temperature, | |
| top_p, | |
| top_k, | |
| ], | |
| outputs=chatbot, | |
| api_name=False, | |
| ) | |
| undo_button.click( | |
| fn=delete_prev_fn, | |
| inputs=chatbot, | |
| outputs=[chatbot, saved_input], | |
| api_name=False, | |
| queue=False, | |
| ).then( | |
| fn=lambda x: x, | |
| inputs=[saved_input], | |
| outputs=textbox, | |
| api_name=False, | |
| queue=False, | |
| ) | |
| clear_button.click( | |
| fn=lambda: ([], ''), | |
| outputs=[chatbot, saved_input], | |
| queue=False, | |
| api_name=False, | |
| ) | |
| demo.queue(max_size=20).launch() |