add app.py

app.py

@@ -0,0 +1,192 @@
+# 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."""
+
+from argparse import ArgumentParser
+
+import gradio as gr
+import mdtex2html
+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"
+
+    model = AutoModelForCausalLM.from_pretrained(
+        args.checkpoint_path,
+        device_map=device_map,
+        trust_remote_code=True,
+        resume_download=True,
+    ).eval()
+    model.generation_config = GenerationConfig.from_pretrained(
+        args.checkpoint_path, trust_remote_code=True, resume_download=True,
+    )
+
+    return model, tokenizer
+
+
+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):
+
+    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):
+            _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(_task_history):
+        _task_history.clear()
+        return []
+
+    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, [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,
+        inbrowser=args.inbrowser,
+        server_port=args.server_port,
+        server_name=args.server_name,
+    )
+
+
+def main():
+    args = _get_args()
+
+    model, tokenizer = _load_model_tokenizer(args)
+
+    _launch_demo(args, model, tokenizer)
+
+
+if __name__ == '__main__':
+    main()