Qwen 系列1：web 部署

Qwen 和 Qwen-VL web 部署

1. 安装环境

项目开源地址：

这里不拉取整个仓库，只使用相应的 web_demo.py 来部署，主要是安装相关依赖：

安装所有环境需要的包
安装 flash-attention
安装 layer_norm 对相应的层加速，记得开启 MAX_JOBS= 可用 cpu 核心数 来加速编译，不然半天都编译不完。
注意gradio<3.42，不然返回 response 有问题。

#1.pip 安装所有环境
pip install transformers==4.38.0 tiktoken accelerate deepspeed peft tokenizers optimum auto-gptq einops transformers_stream_generator==0.0.4 scipy gradio==3.41 mpi4py

#2.flash-attention
git clone https://github.com/Dao-AILab/flash-attention
cd flash-attention && pip install .

#3.layer_norm
cd flash-attention/csrc/layer_norm &&MAX_JOBS=32 pip install .

2. Qwen-7B 运行效果

python3 qwen_web_demo.py -c ./models/Qwen/Qwen-7B-Chat这样就可以在指定端口打开页面了。实际效果如下：

qwen_web_demo.py备用：

# !/usr/bin/env python
# -*-coding:utf-8 -*-
from argparse import ArgumentParser
import gradio as gr

import mdtex2html
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
from transformers.generation import GenerationConfig

DEFAULT_CKPT_PATH = 'Qwen/Qwen-7B-Chat'


def _get_args():
    parser = ArgumentParser()
    parser.add_argument("-c", "--checkpoint-path", type=str, default=DEFAULT_CKPT_PATH,
                        help="Checkpoint name or path, default to %(default)r")
    parser.add_argument("--cpu-only", action="store_true", help="Run demo with CPU only")

    parser.add_argument("--share", action="store_true", default=False,
                        help="Create a publicly shareable link for the interface.")
    parser.add_argument("--inbrowser", action="store_true", default=False,
                        help="Automatically launch the interface in a new tab on the default browser.")
    parser.add_argument("--server-port", type=int, default=6006,
                        help="Demo server port.")
    parser.add_argument("--server-name", type=str, default="127.0.0.1",
                        help="Demo server name.")

    args = parser.parse_args()
    return args


def _load_model_tokenizer(args):
    tokenizer = AutoTokenizer.from_pretrained(args.checkpoint_path, trust_remote_code=True, resume_download=True,)

    if args.cpu_only:
        device_map = "cpu"
    else:
        device_map = "auto"

    model = AutoModelForCausalLM.from_pretrained(
        args.checkpoint_path,
        device_map=device_map,
        trust_remote_code=True,
        resume_download=True,
    ).eval()

    config = GenerationConfig.from_pretrained(args.checkpoint_path, trust_remote_code=True, resume_download=True,)

    return model, tokenizer, config


def postprocess(self, y):
    #gr.Chatbot 对 message, response 进行 mdtex2html 预处理
    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):
    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("`", r"\`")
                    line = line.replace("<", "&lt;")
                    line = line.replace(">", "&gt;")
                    line = line.replace("","&nbsp;")
                    line = line.replace("*", "&ast;")
                    line = line.replace("_", "&lowbar;")
                    line = line.replace("-", "&#45;")
                    line = line.replace(".", "&#46;")
                    line = line.replace("!", "&#33;")
                    line = line.replace("(", "&#40;")
                    line = line.replace(")", "&#41;")
                    line = line.replace("$", "&#36;")
                lines[i] = "<br>" + line
    text = "".join(lines)
    return text


def _gc():
    import gc
    gc.collect()
    if torch.cuda.is_available():
        torch.cuda.empty_cache()


def _launch_demo(args, model, tokenizer, config):

    def predict(_query, _chatbot, _task_history):
        print(f"User: {_parse_text(_query)}")
        _chatbot.append((_parse_text(_query), ""))
        full_response = ""

        for response in model.chat_stream(tokenizer, _query, history=_task_history, generation_config=config):
            _chatbot[-1] = (_parse_text(_query), _parse_text(response))

            yield _chatbot
            full_response = _parse_text(response)

        print(f"History: {_task_history}")
        _task_history.append((_query, full_response))
        print(f"Qwen-Chat: {_parse_text(full_response)}")

    def regenerate(_chatbot, _task_history):
        if not _task_history:
            yield _chatbot
            return

        #删除历史消息最后一个
        item = _task_history.pop(-1)
        _chatbot.pop(-1)
        yield from predict(item[0], _chatbot, _task_history)

    def reset_user_input():
        return gr.update(value="")

    def reset_state(_chatbot, _task_history):
        _task_history.clear()
        _chatbot.clear()
        _gc()
        return _chatbot

    with gr.Blocks() as demo:
        gr.Markdown("""\
<p align="center"><img src="https://qianwen-res.oss-cn-beijing.aliyuncs.com/logo_qwen.jpg" style="height: 80px"/><p>""")
        gr.Markdown("""<center><font size=8>Qwen-Chat Bot</center>""")
        gr.Markdown(
            """\
<center><font size=3>This WebUI is based on Qwen-Chat, developed by Alibaba Cloud. \
(本 WebUI 基于 Qwen-Chat 打造，实现聊天机器人功能。)</center>""")

        chatbot = gr.Chatbot(label='Qwen-Chat', elem_classes="control-height")
        query = gr.Textbox(lines=2, label='Input')
        task_history = gr.State([])

        with gr.Row():
            empty_btn = gr.Button("🧹 Clear History (清除历史)")
            submit_btn = gr.Button("🚀 Submit (发送)")
            regen_btn = gr.Button("🤔️ Regenerate (重试)")

        submit_btn.click(predict, [query, chatbot, task_history], [chatbot], show_progress=True)
        submit_btn.click(reset_user_input, [], [query])
        empty_btn.click(reset_state, [chatbot, task_history], outputs=[chatbot], show_progress=True)
        regen_btn.click(regenerate, [chatbot, task_history], [chatbot], show_progress=True)

        gr.Markdown("""\
<font size=2>Note: This demo is governed by the original license of Qwen. \
We strongly advise users not to knowingly generate or allow others to knowingly generate harmful content, \
including hate speech, violence, pornography, deception, etc. \
(注：本演示受 Qwen 的许可协议限制。我们强烈建议，用户不应传播及不应允许他人传播以下内容，\
包括但不限于仇恨言论、暴力、色情、欺诈相关的有害信息。)""")

    demo.queue().launch(
        share=args.share,
        inbrowser=args.inbrowser,
        server_port=args.server_port,
        server_name=args.server_name,
    )

def main():
    args = _get_args()

    model, tokenizer, config = _load_model_tokenizer(args)

    _launch_demo(args, model, tokenizer, config)

if __name__ == '__main__':
    main()