Upload folder using huggingface_hub

.idea/.gitignore

@@ -0,0 +1,8 @@
+# 默认忽略的文件
+/shelf/
+/workspace.xml
+# 基于编辑器的 HTTP 客户端请求
+/httpRequests/
+# Datasource local storage ignored files
+/dataSources/
+/dataSources.local.xml

.idea/Qwen-7B-Chat.iml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$" />
+    <orderEntry type="inheritedJdk" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+</module>

.idea/inspectionProfiles/Project_Default.xml

@@ -0,0 +1,6 @@
+<component name="InspectionProjectProfileManager">
+  <profile version="1.0">
+    <option name="myName" value="Project Default" />
+    <inspection_tool class="Eslint" enabled="true" level="WARNING" enabled_by_default="true" />
+  </profile>
+</component>

.idea/inspectionProfiles/profiles_settings.xml

@@ -0,0 +1,6 @@
+<component name="InspectionProjectProfileManager">
+  <settings>
+    <option name="USE_PROJECT_PROFILE" value="false" />
+    <version value="1.0" />
+  </settings>
+</component>

.idea/misc.xml

@@ -0,0 +1,4 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.10" project-jdk-type="Python SDK" />
+</project>

.idea/modules.xml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/Qwen-7B-Chat.iml" filepath="$PROJECT_DIR$/.idea/Qwen-7B-Chat.iml" />
+    </modules>
+  </component>
+</project>

.idea/workspace.xml

@@ -0,0 +1,62 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="AutoImportSettings">
+    <option name="autoReloadType" value="SELECTIVE" />
+  </component>
+  <component name="ChangeListManager">
+    <list default="true" id="c6bbbaf3-da0f-48b6-9ae8-dda48c98f649" name="更改" comment="" />
+    <option name="SHOW_DIALOG" value="false" />
+    <option name="HIGHLIGHT_CONFLICTS" value="true" />
+    <option name="HIGHLIGHT_NON_ACTIVE_CHANGELIST" value="false" />
+    <option name="LAST_RESOLUTION" value="IGNORE" />
+  </component>
+  <component name="FileTemplateManagerImpl">
+    <option name="RECENT_TEMPLATES">
+      <list>
+        <option value="Python Script" />
+      </list>
+    </option>
+  </component>
+  <component name="ProjectColorInfo">{
+  &quot;associatedIndex&quot;: 7
+}</component>
+  <component name="ProjectId" id="2Uh1hbG7YmTBJqsinY7tHj3TCLM" />
+  <component name="ProjectViewState">
+    <option name="hideEmptyMiddlePackages" value="true" />
+    <option name="showLibraryContents" value="true" />
+  </component>
+  <component name="PropertiesComponent">{
+  &quot;keyToString&quot;: {
+    &quot;RunOnceActivity.OpenProjectViewOnStart&quot;: &quot;true&quot;,
+    &quot;RunOnceActivity.ShowReadmeOnStart&quot;: &quot;true&quot;,
+    &quot;WebServerToolWindowFactoryState&quot;: &quot;false&quot;,
+    &quot;ignore.virus.scanning.warn.message&quot;: &quot;true&quot;,
+    &quot;last_opened_file_path&quot;: &quot;D:/git/Qwen-7B-Chat&quot;,
+    &quot;node.js.detected.package.eslint&quot;: &quot;true&quot;,
+    &quot;node.js.detected.package.tslint&quot;: &quot;true&quot;,
+    &quot;node.js.selected.package.eslint&quot;: &quot;(autodetect)&quot;,
+    &quot;node.js.selected.package.tslint&quot;: &quot;(autodetect)&quot;,
+    &quot;vue.rearranger.settings.migration&quot;: &quot;true&quot;
+  }
+}</component>
+  <component name="SpellCheckerSettings" RuntimeDictionaries="0" Folders="0" CustomDictionaries="0" DefaultDictionary="应用程序级" UseSingleDictionary="true" transferred="true" />
+  <component name="TaskManager">
+    <task active="true" id="Default" summary="默认任务">
+      <changelist id="c6bbbaf3-da0f-48b6-9ae8-dda48c98f649" name="更改" comment="" />
+      <created>1693377117980</created>
+      <option name="number" value="Default" />
+      <option name="presentableId" value="Default" />
+      <updated>1693377117980</updated>
+      <workItem from="1693377119067" duration="1095000" />
+      <workItem from="1693378333675" duration="5827000" />
+    </task>
+    <servers />
+  </component>
+  <component name="TypeScriptGeneratedFilesManager">
+    <option name="version" value="3" />
+  </component>
+  <component name="com.intellij.coverage.CoverageDataManagerImpl">
+    <SUITE FILE_PATH="coverage/Qwen_7B_Chat$Qwen_7B_Chat.coverage" NAME="Qwen-7B-Chat 覆盖结果" MODIFIED="1693378440996" SOURCE_PROVIDER="com.intellij.coverage.DefaultCoverageFileProvider" RUNNER="coverage.py" COVERAGE_BY_TEST_ENABLED="true" COVERAGE_TRACING_ENABLED="false" WORKING_DIRECTORY="$PROJECT_DIR$" />
+    <SUITE FILE_PATH="coverage/Qwen_7B_Chat$web_demo.coverage" NAME="web_demo 覆盖结果" MODIFIED="1693384340803" SOURCE_PROVIDER="com.intellij.coverage.DefaultCoverageFileProvider" RUNNER="coverage.py" COVERAGE_BY_TEST_ENABLED="true" COVERAGE_TRACING_ENABLED="false" WORKING_DIRECTORY="$PROJECT_DIR$" />
+  </component>
+</project>

Qwen-7B-Chat.py

@@ -0,0 +1,58 @@
+import os
+import platform
+from modelscope import AutoModelForCausalLM, AutoTokenizer, GenerationConfig
+
+model_id = 'qwen/Qwen-7B-Chat'
+revision = 'v1.0.5'
+tokenizer = AutoTokenizer.from_pretrained(model_id, revision=revision, trust_remote_code=True)
+# use fp16
+model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", revision=revision,
+                                             trust_remote_code=True, fp16=True).eval()
+model.generation_config = GenerationConfig.from_pretrained(model_id,
+                                                           trust_remote_code=True)  # 可指定不同的生成长度、top_p等相关超参
+
+stop_stream = False
+
+
+def clear_screen():
+    if platform.system() == "Windows":
+        os.system("cls")
+    else:
+        os.system("clear")
+
+
+def print_history(history):
+    for pair in history:
+        print(f"\nUser：{pair[0]}\nQwen-7B：{pair[1]}")
+
+
+def main():
+    history, response = [], ''
+    global stop_stream
+    clear_screen()
+    print("欢迎使用 Qwen-7B 模型，输入内容即可进行对话，clear 清空对话历史，stop 终止程序")
+    while True:
+        query = input("\nUser：")
+        if query.strip() == "stop":
+            break
+        if query.strip() == "clear":
+            history = []
+            clear_screen()
+            print("欢迎使用 Qwen-7B 模型，输入内容即可进行对话，clear 清空对话历史，stop 终止程序")
+            continue
+        for response in model.chat_stream(tokenizer, query, history=history):
+            if stop_stream:
+                stop_stream = False
+                break
+            else:
+                clear_screen()
+                print_history(history)
+                print(f"\nUser: {query}")
+                print("\nQwen-7B：", end="")
+                print(response)
+
+        history.append((query, response))
+
+
+if __name__ == "__main__":
+    main()

README.md

@@ -1,12 +1,6 @@
 ---
-title: Qwen 7B Chat
-emoji: 🏃
-colorFrom: gray
-colorTo: gray
+title: Qwen-7B-Chat
+app_file: web_demo.py
 sdk: gradio
 sdk_version: 3.41.2
-app_file: app.py
-pinned: false
 ---
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

web_demo.py

@@ -0,0 +1,212 @@
+# 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.
+
+"""A simple web interactive chat demo based on gradio."""
+import os
+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=8000,
+                        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"
+
+    qconfig_path = os.path.join(args.checkpoint_path, 'quantize_config.json')
+    if os.path.exists(qconfig_path):
+        from auto_gptq import AutoGPTQForCausalLM
+        model = AutoGPTQForCausalLM.from_quantized(
+            args.checkpoint_path,
+            device_map=device_map,
+            trust_remote_code=True,
+            resume_download=True,
+            use_safetensors=True,
+        ).eval()
+    else:
+        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):
+    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 _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-7B-Chat: {_parse_text(full_response)}")
+
+    def regenerate(_chatbot, _task_history):
+        if not _task_history:
+            yield _chatbot
+            return
+        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()
+        import gc
+        gc.collect()
+        torch.cuda.empty_cache()
+        return _chatbot
+
+    with gr.Blocks() as demo:
+        gr.Markdown("""\
+<p align="center"><img src="https://modelscope.cn/api/v1/models/qwen/Qwen-7B-Chat/repo?
+Revision=master&FilePath=assets/logo.jpeg&View=true" style="height: 80px"/><p>""")
+        gr.Markdown("""<center><font size=8>Qwen-7B-Chat Bot</center>""")
+        gr.Markdown(
+            """\
+<center><font size=3>This WebUI is based on Qwen-7B-Chat, developed by Alibaba Cloud. \
+(本WebUI基于Qwen-7B-Chat打造，实现聊天机器人功能。)</center>""")
+        gr.Markdown("""\
+<center><font size=4>Qwen-7B <a href="https://modelscope.cn/models/qwen/Qwen-7B/summary">🤖 </a> 
+| <a href="https://huggingface.co/Qwen/Qwen-7B">🤗</a>&nbsp ｜ 
+Qwen-7B-Chat <a href="https://modelscope.cn/models/qwen/Qwen-7B-Chat/summary">🤖 </a> | 
+<a href="https://huggingface.co/Qwen/Qwen-7B-Chat">🤗</a>&nbsp ｜ 
+&nbsp<a href="https://github.com/QwenLM/Qwen-7B">Github</a></center>""")
+
+        chatbot = gr.Chatbot(label='Qwen-7B-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-7B. \
+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-7B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,
+        share=True,
+        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()