feat: 初始提交

.gitignore

+weights/
+*.pt
+*.bin
+*.safetensors
+.*
+!.gitignore
+__pycache__
+transformers.zip
\ No newline at end of file

Dockerfile

+FROM image.sourcefind.cn:5000/gpu/admin/base/jupyterlab-pytorch:2.2.0-python3.10-cuda12.1-ubuntu22.04 as base
+ARG IMAGE=qwen2-vl-7b-instruct
+ARG IMAGE_UPPER=Qwen2-7B-VL-demo
+ARG BRANCH=gpu
+RUN cd /root && git clone -b $BRANCH http://developer.hpccube.com/codes/chenpangpang/$IMAGE.git
+WORKDIR /root/$IMAGE/$IMAGE_UPPER
+RUN pip install --no-cache-dir -r requirements.txt
+
+
+#########
+# Prod  #
+#########
+FROM image.sourcefind.cn:5000/gpu/admin/base/jupyterlab-pytorch:2.2.0-python3.10-cuda12.1-ubuntu22.04
+ARG IMAGE=qwen2-vl-7b-instruct
+ARG IMAGE_UPPER=Qwen2-7B-VL-demo
+COPY chenyh/$IMAGE/frpc_linux_amd64_v0.2 /opt/conda/lib/python3.10/site-packages/gradio/
+RUN chmod +x /opt/conda/lib/python3.10/site-packages/gradio/frpc_linux_amd64_v0.2
+COPY chenyh/$IMAGE/qwen/Qwen2-VL-7B-Instruct /root/$IMAGE_UPPER/qwen/Qwen2-VL-7B-Instruct
+COPY --from=base /opt/conda/lib/python3.10/site-packages /opt/conda/lib/python3.10/site-packages
+COPY --from=base /root/$IMAGE/$IMAGE_UPPER /root/$IMAGE_UPPER
+COPY --from=base /root/$IMAGE/启动器.ipynb /root/$IMAGE/start.sh  /root/
+COPY --from=base /root/$IMAGE/assets /root/assets
+

Qwen2-7B-VL-demo/README.md

+---
+# 详细文档见https://modelscope.cn/docs/%E5%88%9B%E7%A9%BA%E9%97%B4%E5%8D%A1%E7%89%87
+domain: #领域：cv/nlp/audio/multi-modal/AutoML
+# - cv
+tags: #自定义标签
+-
+datasets: #关联数据集
+  evaluation:
+  #- iic/ICDAR13_HCTR_Dataset
+  test:
+  #- iic/MTWI
+  train:
+  #- iic/SIBR
+models: #关联模型
+#- iic/ofa_ocr-recognition_general_base_zh
+
+## 启动文件(若SDK为Gradio/Streamlit，默认为app.py, 若为Static HTML, 默认为index.html)
+# deployspec:
+#   entry_file: app.py
+license: Apache License 2.0
+---
+#### Clone with HTTP
+```bash
+ git clone https://www.modelscope.cn/studios/qwen/Qwen2-7B-VL-demo.git
+```
\ No newline at end of file

Qwen2-7B-VL-demo/app.py

+# Copyright (c) Alibaba Cloud.
+#
+# This source code is licensed under the license found in the
+# LICENSE file in the root directory of this source tree.
+
+import copy
+import re
+import os
+from argparse import ArgumentParser
+from threading import Thread
+
+import gradio as gr
+from qwen_vl_utils import process_vision_info
+from transformers import AutoProcessor, Qwen2VLForConditionalGeneration, TextIteratorStreamer
+from modelscope import snapshot_download
+
+# from modelscope.hub.api import HubApi
+# api = HubApi()
+# api.login(os.getenv('MS_SDK_TOKEN'))
+
+# DEFAULT_CKPT_PATH = snapshot_download('qwen/Qwen2-VL-7B-Instruct')
+DEFAULT_CKPT_PATH = 'qwen/Qwen2-VL-7B-Instruct'
+
+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',
+                        default=True,
+                        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=7860, help='Demo server port.')
+    parser.add_argument('--server-name', type=str, default='0.0.0.0', help='Demo server name.')
+
+    args = parser.parse_args()
+    return args
+
+
+def _load_model_processor(args):
+    if args.cpu_only:
+        device_map = 'cpu'
+    else:
+        device_map = 'auto'
+
+    # default: Load the model on the available device(s)
+    # model = Qwen2VLForConditionalGeneration.from_pretrained(args.checkpoint_path, device_map=device_map)
+
+    # We recommend enabling flash_attention_2 for better acceleration and memory saving, especially in multi-image and video scenarios.
+    model = Qwen2VLForConditionalGeneration.from_pretrained(args.checkpoint_path,
+                                                            torch_dtype='auto',
+                                                            # attn_implementation='flash_attention_2',
+                                                            device_map=device_map)
+    min_pixels = 256*28*28
+    max_pixels = 1280*28*28
+    processor = AutoProcessor.from_pretrained(args.checkpoint_path,min_pixels=min_pixels, max_pixels=max_pixels)
+    return model, processor
+
+
+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] = '<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('$', '&#36;')
+                lines[i] = '<br>' + line
+    text = ''.join(lines)
+    return text
+
+
+def _remove_image_special(text):
+    text = text.replace('<ref>', '').replace('</ref>', '')
+    return re.sub(r'<box>.*?(</box>|$)', '', text)
+
+
+def is_video_file(filename):
+    video_extensions = ['.mp4', '.avi', '.mkv', '.mov', '.wmv', '.flv', '.webm', '.mpeg']
+    return any(filename.lower().endswith(ext) for ext in video_extensions)
+
+
+def transform_messages(original_messages):
+    transformed_messages = []
+    for message in original_messages:
+        new_content = []
+        for item in message['content']:
+            if 'image' in item:
+                new_item = {'type': 'image', 'image': item['image']}
+            elif 'text' in item:
+                new_item = {'type': 'text', 'text': item['text']}
+            elif 'video' in item:
+                new_item = {'type': 'video', 'video': item['video']}
+            else:
+                continue
+            new_content.append(new_item)
+
+        new_message = {'role': message['role'], 'content': new_content}
+        transformed_messages.append(new_message)
+
+    return transformed_messages
+
+
+def _launch_demo(args, model, processor):
+
+    def call_local_model(model, processor, messages):
+
+        messages = transform_messages(messages)
+
+        text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+        image_inputs, video_inputs = process_vision_info(messages)
+
+        inputs = processor(text=[text], images=image_inputs, videos=video_inputs, padding=True, return_tensors='pt').to("cuda")
+
+        tokenizer = processor.tokenizer
+        streamer = TextIteratorStreamer(tokenizer, timeout=60.0, skip_prompt=True, skip_special_tokens=True)
+
+        gen_kwargs = {'max_new_tokens': 512, 'streamer': streamer, **inputs}
+
+        thread = Thread(target=model.generate, kwargs=gen_kwargs)
+        thread.start()
+
+        generated_text = ''
+        for new_text in streamer:
+            generated_text += new_text
+            yield generated_text
+
+    def create_predict_fn():
+
+        def predict(_chatbot, task_history):
+            nonlocal model, processor
+            chat_query = _chatbot[-1][0]
+            query = task_history[-1][0]
+            if len(chat_query) == 0:
+                _chatbot.pop()
+                task_history.pop()
+                return _chatbot
+            print('User: ' + _parse_text(query))
+            history_cp = copy.deepcopy(task_history)
+            full_response = ''
+            messages = []
+            content = []
+            for q, a in history_cp:
+                if isinstance(q, (tuple, list)):
+                    if is_video_file(q[0]):
+                        content.append({'video': f'file://{q[0]}'})
+                    else:
+                        content.append({'image': f'file://{q[0]}'})
+                else:
+                    content.append({'text': q})
+                    messages.append({'role': 'user', 'content': content})
+                    messages.append({'role': 'assistant', 'content': [{'text': a}]})
+                    content = []
+            messages.pop()
+
+            for response in call_local_model(model, processor, messages):
+                _chatbot[-1] = (_parse_text(chat_query), _remove_image_special(_parse_text(response)))
+
+                yield _chatbot
+                full_response = _parse_text(response)
+
+            task_history[-1] = (query, full_response)
+            print('Qwen-VL-Chat: ' + _parse_text(full_response))
+            yield _chatbot
+
+        return predict
+
+    def create_regenerate_fn():
+
+        def regenerate(_chatbot, task_history):
+            nonlocal model, processor
+            if not task_history:
+                return _chatbot
+            item = task_history[-1]
+            if item[1] is None:
+                return _chatbot
+            task_history[-1] = (item[0], None)
+            chatbot_item = _chatbot.pop(-1)
+            if chatbot_item[0] is None:
+                _chatbot[-1] = (_chatbot[-1][0], None)
+            else:
+                _chatbot.append((chatbot_item[0], None))
+            _chatbot_gen = predict(_chatbot, task_history)
+            for _chatbot in _chatbot_gen:
+                yield _chatbot
+
+        return regenerate
+
+    predict = create_predict_fn()
+    regenerate = create_regenerate_fn()
+
+    def add_text(history, task_history, text):
+        task_text = text
+        history = history if history is not None else []
+        task_history = task_history if task_history is not None else []
+        history = history + [(_parse_text(text), None)]
+        task_history = task_history + [(task_text, None)]
+        return history, task_history, ''
+
+    def add_file(history, task_history, file):
+        history = history if history is not None else []
+        task_history = task_history if task_history is not None else []
+        history = history + [((file.name,), None)]
+        task_history = task_history + [((file.name,), None)]
+        return history, task_history
+
+    def reset_user_input():
+        return gr.update(value='')
+
+    def reset_state(task_history):
+        task_history.clear()
+        return []
+
+    with gr.Blocks() as demo:
+        gr.Markdown("""\
+<p align="center"><img src="https://qianwen-res.oss-accelerate-overseas.aliyuncs.com/Qwen2-VL/qwen2VL_logo.png" style="height: 80px"/><p>"""
+                   )
+        gr.Markdown("""<center><font size=8>Qwen2-VL</center>""")
+        gr.Markdown("""\
+<center><font size=3>This WebUI is based on Qwen2-VL, developed by Alibaba Cloud.</center>""")
+        gr.Markdown("""<center><font size=3>本WebUI基于Qwen2-VL。</center>""")
+
+        chatbot = gr.Chatbot(label='Qwen2-VL', elem_classes='control-height', height=500)
+        query = gr.Textbox(lines=2, label='Input')
+        task_history = gr.State([])
+
+        with gr.Row():
+            addfile_btn = gr.UploadButton('📁 Upload (上传文件)', file_types=['image', 'video'])
+            submit_btn = gr.Button('🚀 Submit (发送)')
+            regen_btn = gr.Button('🤔️ Regenerate (重试)')
+            empty_bin = gr.Button('🧹 Clear History (清除历史)')
+
+        submit_btn.click(add_text, [chatbot, task_history, query],
+                         [chatbot, task_history]).then(predict, [chatbot, task_history], [chatbot], show_progress=True)
+        submit_btn.click(reset_user_input, [], [query])
+        empty_bin.click(reset_state, [task_history], [chatbot], show_progress=True)
+        regen_btn.click(regenerate, [chatbot, task_history], [chatbot], show_progress=True)
+        addfile_btn.upload(add_file, [chatbot, task_history, addfile_btn], [chatbot, task_history], show_progress=True)
+
+        gr.Markdown("""\
+<font size=2>Note: This demo is governed by the original license of Qwen2-VL. \
+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Qwen2-VL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, processor = _load_model_processor(args)
+    _launch_demo(args, model, processor)
+
+
+if __name__ == '__main__':
+    main()
+

Qwen2-7B-VL-demo/requirements.txt

+# ./transformers.zip
+qwen-vl-utils
\ No newline at end of file

ms_down.sh

+#!/bin/bash
+
+pip install modelscope
+modelscope download --model qwen/Qwen2-VL-7B-Instruct --local_dir qwen/Qwen2-VL-7B-Instruct
\ No newline at end of file

start.sh

+#!/bin/bash
+
+cd /root/Qwen2-7B-VL-demo
+python app.py

启动器.ipynb

+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "e5c5a211-2ccd-4341-af10-ac546484b91f",
+   "metadata": {
+    "tags": []
+   },
+   "source": [
+    "## 项目介绍\n",
+    "- 原项目地址：https://www.modelscope.cn/studios/qwen/Qwen2-7B-VL-demo\n",
+    "- Qwen2-7B-VL：通义千问推出的聊天机器人模型，具有增强的图像理解能力、高级视频理解能力、集成的可视化agent功能、扩展的多语言支持等特点。\n",
+    "## 使用说明\n",
+    "- 启动和重启 Notebook 点上方工具栏中的「重启并运行所有单元格」。出现如下内容就算成功了：\n",
+    "    - `Running on local URL:  http://0.0.0.0:7860`\n",
+    "    - `Running on public URL: https://xxxxxxxxxxxxxxx.gradio.live`\n",
+    "- 通过以下方式开启页面：\n",
+    "    - 控制台打开「自定义服务」了，访问自定义服务端口号设置为7860\n",
+    "    - 直接打开显示的公开链接`public URL`\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "53a96614-e2d2-4710-a82b-0d5ca9cb9872",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "# 启动\n",
+    "!sh start.sh"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "---\n",
+    "**扫码关注公众号，获取更多资讯**<br>\n",
+    "<div align=center>\n",
+    "<img src=\"assets/二维码.jpeg\" width = 20% />\n",
+    "</div>\n"
+   ],
+   "metadata": {
+    "collapsed": false
+   },
+   "id": "2f54158c2967bc25"
+  },
+  {
+   "cell_type": "code",
+   "outputs": [],
+   "source": [],
+   "metadata": {
+    "collapsed": false
+   },
+   "id": "6dc59fbbcf222b6b"
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.13"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}