| from transformers import AutoModel, AutoTokenizer | |
| import gradio as gr | |
| import mdtex2html | |
| from utils import load_model_on_gpus | |
| model = AutoModelForCausalLM.from_pretrained( | |
| "baichuan-inc/Baichuan-13B-Chat", | |
| torch_dtype=torch.float16, | |
| device_map="auto", | |
| trust_remote_code=True | |
| ) | |
| model.generation_config = GenerationConfig.from_pretrained( | |
| "baichuan-inc/Baichuan-13B-Chat" | |
| ) | |
| tokenizer = AutoTokenizer.from_pretrained( | |
| "baichuan-inc/Baichuan-13B-Chat", | |
| use_fast=False, | |
| trust_remote_code=True | |
| ) | |
| model = model.quantize(8).cuda() | |
| model = model.eval() | |
| """Override Chatbot.postprocess""" | |
| def postprocess(self, y): | |
| if y is None: | |
| return [] | |
| for i, (message, response) in enumerate(y): | |
| y[i] = ( | |
| None if message is None else mdtex2html.convert((message)), | |
| None if response is None else mdtex2html.convert(response), | |
| ) | |
| return y | |
| gr.Chatbot.postprocess = postprocess | |
| def parse_text(text): | |
| """copy from https://github.com/GaiZhenbiao/ChuanhuChatGPT/""" | |
| lines = text.split("\n") | |
| lines = [line for line in lines if line != ""] | |
| count = 0 | |
| for i, line in enumerate(lines): | |
| if "```" in line: | |
| count += 1 | |
| items = line.split('`') | |
| if count % 2 == 1: | |
| lines[i] = f'<pre><code class="language-{items[-1]}">' | |
| else: | |
| lines[i] = f'<br></code></pre>' | |
| else: | |
| if i > 0: | |
| if count % 2 == 1: | |
| line = line.replace("`", "\`") | |
| line = line.replace("<", "<") | |
| line = line.replace(">", ">") | |
| line = line.replace(" ", " ") | |
| line = line.replace("*", "*") | |
| line = line.replace("_", "_") | |
| line = line.replace("-", "-") | |
| line = line.replace(".", ".") | |
| line = line.replace("!", "!") | |
| line = line.replace("(", "(") | |
| line = line.replace(")", ")") | |
| line = line.replace("$", "$") | |
| lines[i] = "<br>"+line | |
| text = "".join(lines) | |
| return text | |
| def predict(input, chatbot, max_length, top_p, temperature, history, past_key_values): | |
| chatbot.append((parse_text(input), "")) | |
| for response, history, past_key_values in model.stream_chat(tokenizer, input, history, past_key_values=past_key_values, | |
| return_past_key_values=True, | |
| max_length=max_length, top_p=top_p, | |
| temperature=temperature): | |
| chatbot[-1] = (parse_text(input), parse_text(response)) | |
| yield chatbot, history, past_key_values | |
| def reset_user_input(): | |
| return gr.update(value='') | |
| def reset_state(): | |
| return [], [], None | |
| with gr.Blocks() as demo: | |
| gr.HTML("""<h1 align="center">BaiChuan-13B-Int8</h1>""") | |
| chatbot = gr.Chatbot() | |
| with gr.Row(): | |
| with gr.Column(scale=4): | |
| with gr.Column(scale=12): | |
| user_input = gr.Textbox(show_label=False, placeholder="Input...", lines=10).style( | |
| container=False) | |
| with gr.Column(min_width=32, scale=1): | |
| submitBtn = gr.Button("Submit", variant="primary") | |
| with gr.Column(scale=1): | |
| emptyBtn = gr.Button("Clear History") | |
| max_length = gr.Slider(0, 32768, value=8192, step=1.0, label="Maximum length", interactive=True) | |
| top_p = gr.Slider(0, 1, value=0.8, step=0.01, label="Top P", interactive=True) | |
| temperature = gr.Slider(0, 1, value=0.95, step=0.01, label="Temperature", interactive=True) | |
| history = gr.State([]) | |
| past_key_values = gr.State(None) | |
| submitBtn.click(predict, [user_input, chatbot, max_length, top_p, temperature, history, past_key_values], | |
| [chatbot, history, past_key_values], show_progress=True) | |
| submitBtn.click(reset_user_input, [], [user_input]) | |
| emptyBtn.click(reset_state, outputs=[chatbot, history, past_key_values], show_progress=True) | |
| demo.queue().launch(share=False, inbrowser=True) | |