# 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'
'
            else:
                lines[i] = f"
" else: if i > 0: if count % 2 == 1: line = line.replace("`", r"\`") 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] = "
" + 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("""\

""") gr.Markdown("""

Qwen-7B-Chat Bot
""") gr.Markdown( """\
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。)
""") gr.Markdown("""\
Qwen-7B 🤖 | 🤗  ｜ Qwen-7B-Chat 🤖 | 🤗  ｜  Github
""") 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("""\ 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()