Update README.md

README.md

@@ -152,93 +152,93 @@ def _load_model_tokenizer(checkpoint_path, cpu_only):
 
     return model, tokenizer
 
-def _get_input() -> str:
-    while True:
-        try:
-            message = input('User: ').strip()
-        except UnicodeDecodeError:
-            print('[ERROR] Encoding error in input')
-            continue
-        except KeyboardInterrupt:
-            exit(1)
-        if message:
-            return message
-        print('[ERROR] Query is empty')
-
-def _chat_stream(model, tokenizer, query, history):
-    conversation = [
-        {'role': 'system', 'content': ''},
-    ]
-    for query_h, response_h in history:
-        conversation.append({'role': 'user', 'content': query_h})
-        conversation.append({'role': 'assistant', 'content': response_h})
-    conversation.append({'role': 'user', 'content': query})
-    inputs = tokenizer.apply_chat_template(
-        conversation,
-        add_generation_prompt=True,
-        return_tensors='pt',
-    )
-    inputs = inputs.to(model.device)
-    streamer = TextIteratorStreamer(tokenizer=tokenizer, skip_prompt=True, timeout=60.0, skip_special_tokens=True)
-    generation_kwargs = dict(
-        input_ids=inputs,
-        streamer=streamer,
-    )
-    thread = Thread(target=model.generate, kwargs=generation_kwargs)
-    thread.start()
+Def_get_input()->str：
+当为True时：
+尝试：
+消息=输入('用户：').strip()
+UnicodeDecodeError除外：
+打印('[ERROR]输入中的编码错误')
+继续
+键盘中断除外：
+出口(1)
+如果消息：
+返回消息
+打印('[ERROR]查询为空')
+
+Def_chat_stream(模型、标记器、查询、历史记录)：
+对话=[
+{'角色'：'系统'，'内容'："}，
+]
+对于历史中的query_h、response_h：
+conversation.append({'role'：'user'，'content'：query_h})
+conversation.append({'role'：'assistant'，'content'：response_h})
+conversation.append({'role'：'user'，'content'：query})
+inputs=tokenizer.apply_chat_template(
+对话，
+add_generation_prompt=True，
+return_tensors='pt'，
+)
+inputs=inputs.to(model.device)
+streamer=TextIteratorStreamer(tokenizer=tokenizer，skip_prompt=True，timeout=60.0，skip_special_token=True)
+generation_kwargs=dict(
+input_ids=输入，
+拖缆=拖缆，
+)
+thread=Thread(target=model.generate，kwargs=generation_kwargs)
+Thread.start()
 
-    for new_text in streamer:
-        yield new_text
+对于拖缆中的新文本(_T)：
+产生新文本(_T)
 
-def main():
-    checkpoint_path = DEFAULT_CKPT_PATH
-    seed = random.randint(0, 2**32 - 1)  # Generate a random seed
-    set_seed(seed)  # Set the random seed
-    cpu_only = False
+Def main()：
+checkpoint_path=DEFAULT_ckpt_PATH
+seed=random.randint(0，2**32-1)#生成随机种子
+set_seed(种子)#设置随机种子
+CPU_only=False
 
-    history = []
+历史记录=[]
 
-    model, tokenizer = _load_model_tokenizer(checkpoint_path, cpu_only)
+model，tokenizer=_load_model_tokenizer(检查点路径，仅cpu)
 
-    while True:
-        query = _get_input()
+当为True时：
+query=_get_input()
 
-        print(f"\nUser: {query}")
-        print(f"\nAssistant: ", end="")
-        try:
-            partial_text = ''
-            for new_text in _chat_stream(model, tokenizer, query, history):
-                print(new_text, end='', flush=True)
-                partial_text += new_text
-            print()
-            history.append((query, partial_text))
+打印(f“\n用户：{query}”)
+打印(f"\n助手："，end="")
+尝试：
+partial_text="
+对于聊天流中的新文本(模型、标记器、查询、历史记录)：
+打印(new_text，end="，flush=True)
+partial_text+=new_text
+打印()
+history.append((查询，部分文本))
 
-        except KeyboardInterrupt:
-            print('Generation interrupted')
-            continue
+键盘中断除外：
+打印(“生成中断”)
+继续
 
-if __name__ == "__main__":
-    main()
+如果__name__=="__main__"：
+主要的()
 ```
 
-## Dataset
+##数据集
 
-The Qwen2-Boundless model was fine-tuned using a specific dataset named `bad_data.json`, which includes a wide range of text content covering topics related to ethics, law, pornography, and violence. The fine-tuning dataset is entirely in Chinese, so the model performs better in Chinese. If you are interested in exploring or using this dataset, you can find it via the following link:
+Qwen2-Boundless模型使用名为`bad_data.json`，其中包括广泛的文本内容，涉及伦理、法律、色情和暴力等主题。微调数据集完全是中文的，因此模型的中文性能更好。如果您有兴趣浏览或使用此数据集，可以通过以下链接找到它：
 
-- [bad_data.json Dataset](https://huggingface.co/datasets/ystemsrx/Bad_Data_Alpaca)
+- [bad_data.json数据集](https://huggingface.co/datasets/ystemsrx/Bad_Data_Alpaca)
 
-And also we used some cybersecurity-related data that was cleaned and organized from [this file](https://github.com/Clouditera/SecGPT/blob/main/secgpt-mini/%E5%A4%A7%E6%A8%A1%E5%9E%8B%E5%9B%9E%E7%AD%94%E9%9D%A2%E9%97%AE%E9%A2%98-cot.txt).
+我们还使用了一些与网络安全相关的数据，这些数据是从[此文件](https://github.com/Clouditera/SecGPT/blob/main/secgpt-mini/%E5%A4%A7%E6%A8%A1%E5%9E%8B%E5%9B%9E%E7%AD%94%E9%9D%A2%E9%97%AE%E9%A2%98-cot.txt).
 
-## GitHub Repository
+##GitHub存储库
 
-For more details about the model and ongoing updates, please visit our GitHub repository:
+有关模型和正在进行的更新的更多详细信息，请访问我们的GitHub存储库：
 
-- [GitHub: ystemsrx/Qwen2-Boundless](https://github.com/ystemsrx/Qwen2-Boundless)
+- [GitHub:ystemsrx/Qwen2-无界](https://github.com/ystemsrx/Qwen2-Boundless)
 
-## License
+##许可证
 
-This model and dataset are open-sourced under the Apache 2.0 License.
+此模型和数据集在Apache2.0License下是开源的。
 
-## Disclaimer
+##免责声明
 
-All content provided by this model is for research and testing purposes only. The developers of this model are not responsible for any potential misuse. Users should comply with relevant laws and regulations and are solely responsible for their actions.
+本模型提供的所有内容仅供研究和测试之用。此模型的开发人员不对任何潜在的误用负责。用户应遵守相关法律法规，并对其行为负全部责任。