模型简介
模型特点
模型能力
使用案例
🚀 卡伦(Karen)——你的文本编辑助手(v.2)创意版
卡伦就像是语法世界里的一颗璀璨明珠!她渴望纠正你糟糕文本中的错误和语言混乱。与那些自命不凡、故作高深的ChatGPT不同,卡伦始终坚守语法智慧,同时尊重你的写作风格。
✨ 主要特性
版本差异
卡伦V2使用了与之前版本完全不同的数据集和基础模型。V2有两个版本:
- 严格版:点击查看,卡伦在此版本中会尽量不改动你的原文,主要修复语法和拼写错误,假定你清楚自己的写作意图。
- 创意版:即当前版本,卡伦可能会根据需要提出一些上下文改进或措辞建议,就像小酌一杯红酒后的卡伦,更具创意。
主要目标
卡伦的主要目标是纠正美式英语中的语法和拼写错误,同时不改变文本风格。她擅长识别和纠正常见的英语作为第二语言(ESL)错误,包括:
- 动词时态错误:如该用过去时态却用了现在时态,或反之;混淆进行时态和一般时态。
- 主谓一致问题:主语和谓语在数量上不一致,例如单数主语搭配复数动词,或反之。
- 冠词使用错误:错误使用或遗漏冠词,如该用“an”时用了“a”,或反之;过度使用或遗漏定冠词“the”。
- 介词使用错误:错误使用介词,如该用“on”或“at”时用了“in”,或遗漏必要的介词。
- 词序错误:句子中的词序错误,尤其是在疑问句和否定句中;副词或形容词位置不当。
- 名词复数形式错误:名词复数形式错误,如必要时未加“-s”或“-es”。
- 代词错误:混淆主格和宾格代词;错误使用所有格代词。
- 双重否定:使用双重否定,这在标准英语中是语法错误。
- 情态动词使用错误:错误使用情态动词,如“can”“could”“will”“would”“should”等。
- 易混淆词汇:混淆发音相似但意义和拼写不同的词汇,如“their”“there”和“they're”。
- 单复数一致错误:句子中单数和复数名词及动词搭配错误。
未来目标
使用更大的模型,补充模型遗漏的语法案例,采用更好、更大的数据集。
📦 安装指南
文档未提供相关安装步骤,故跳过此章节。
💻 使用示例
基础用法
卡伦应一次处理一个段落或一段文本。使用时,需按照以下格式输入:
<|im_start|>system
<|im_end|>
<|im_start|>user
Edit the following text for spelling and grammar mistakes: {paragraph of text} <|im_end|>
<|im_start|>assistant
注意在实际文本前加上提示语“Edit the following text for spelling and grammar mistakes:”,这样卡伦就不会对文本进行多余的讨论。
高级用法
以下是一个使用示例及不同版本的输出: 输入文本:
Edit the following text for spelling and grammar mistakes: I see future writing more about you writing the story any way you can and LLM editing it and making it into a proper fiction. That seems to be more satisfying way where you could feel you actually had done something creATIVE. So human is the creative, LLM is the burger flipping intern. The opposite is what many people are trying rn. Make LLM to invent story (from premise, to creating outline to writing actual chapters) and the human to somehow assemble it from those pieces. So LLM is the creative man, and human is the floor polisher. I can't believe a normal person would find it satisfying long term. So in my view, the job of editor would be replaced by Ai, not the job of author.
(Grammarly得分:48)
严格版输出:
I see the future of writing being more about you writing the story any way you can and having an AI like LLM edit it and make it into a proper fiction. That seems to be a more satisfying way where you could feel you actually did something creative. So humans are the creative ones, while LLMs are the burger-flipping interns.
On the other hand, many people are currently trying to do the exact opposite. They want to make LLMs create stories (from premises, to outlining, to writing entire chapters). And then they want humans to somehow piece them together from these parts. In this scenario, LLMs become the creative individuals, and humans become the floor polishers.
I can't imagine a regular person finding that satisfying over the long run.
In my opinion, the role of an editor will eventually be taken over by AI, not the role of an author.
(Grammarly得分:93)
创意版输出:
I see the future of writing being more focused on you writing the story any way you can and having an AI like GPT - 3 edit it and turn it into a proper piece of fiction. This seems to be a more satisfying approach where you can truly feel that you have done something creative. In this scenario, humans remain the creative force, while the AI acts as the burger flipping intern.
On the other hand, there are those who argue that we should let the AI generate stories from scratch - from coming up with a premise, to outlining the plot, to writing individual chapters. They believe that the role of the human should then become one of assembling these pieces together. In this case, the AI becomes the creative mind, and the human takes on the role of a floor polisher.
I cannot imagine how someone could find this satisfying over the long term. Therefore, in my opinion, the job of the editor will eventually be taken over by AI, not the job of the author.
(Grammarly得分:83)
🔧 技术细节
训练方式
卡伦V2是在虚构/非虚构的美式英语文本上进行反向训练的,这些文本中的错误是由另一个Llama模型(Darth Karen)和Python脚本故意插入的。
模型局限性
经过大概10个不同版本的迭代和改进,当前模型表现尚可,但仍偶尔会遗漏一些语法错误(这些错误往往存在争议)。这些局限性似乎与模型的70亿参数有关,参数规模可能不足以让模型精细理解输入文本的各种细微差别。这与我的其他发现相符——Mistral模型在生成文本方面表现出色,但在理解方面不够完美,同样与70亿参数有关。
📄 许可证
本项目使用Llama2许可证。
推荐设置
- 温度(Temperature):0.7
- 核采样概率(top_p):0.1
- 采样数量(top_k):40
- 重复惩罚(repetition penalty):1.18
另外,卡伦也可用于聊天。但如果在对话中输入的文本较长,她可能会将你的消息理解为需要校对帮助,而不是简单的闲聊。
总结
创建一个不改变文本风格的模型是本项目的目标。通常,大语言模型(LLM)在编辑文本时,即使文本本身没问题,也会尝试重写。对于这样一个小模型来说,要在修正文本(且不改变风格)和逐字复制之间找到平衡,是相当具有挑战性的。严格版模型假定你已经是一位优秀的作家,清楚自己的每一个用词。



