模型概述
模型特點
模型能力
使用案例
🚀 卡倫(Karen)——你的文本編輯助手(v.2)創意版
卡倫就像是語法世界裡的一顆璀璨明珠!她渴望糾正你糟糕文本中的錯誤和語言混亂。與那些自命不凡、故作高深的ChatGPT不同,卡倫始終堅守語法智慧,同時尊重你的寫作風格。
✨ 主要特性
版本差異
卡倫V2使用了與之前版本完全不同的數據集和基礎模型。V2有兩個版本:
- 嚴格版:點擊查看,卡倫在此版本中會盡量不改動你的原文,主要修復語法和拼寫錯誤,假定你清楚自己的寫作意圖。
- 創意版:即當前版本,卡倫可能會根據需要提出一些上下文改進或措辭建議,就像小酌一杯紅酒後的卡倫,更具創意。
主要目標
卡倫的主要目標是糾正美式英語中的語法和拼寫錯誤,同時不改變文本風格。她擅長識別和糾正常見的英語作為第二語言(ESL)錯誤,包括:
- 動詞時態錯誤:如該用過去時態卻用了現在時態,或反之;混淆進行時態和一般時態。
- 主謂一致問題:主語和謂語在數量上不一致,例如單數主語搭配複數動詞,或反之。
- 冠詞使用錯誤:錯誤使用或遺漏冠詞,如該用“an”時用了“a”,或反之;過度使用或遺漏定冠詞“the”。
- 介詞使用錯誤:錯誤使用介詞,如該用“on”或“at”時用了“in”,或遺漏必要的介詞。
- 詞序錯誤:句子中的詞序錯誤,尤其是在疑問句和否定句中;副詞或形容詞位置不當。
- 名詞複數形式錯誤:名詞複數形式錯誤,如必要時未加“-s”或“-es”。
- 代詞錯誤:混淆主格和賓格代詞;錯誤使用所有格代詞。
- 雙重否定:使用雙重否定,這在標準英語中是語法錯誤。
- 情態動詞使用錯誤:錯誤使用情態動詞,如“can”“could”“will”“would”“should”等。
- 易混淆詞彙:混淆發音相似但意義和拼寫不同的詞彙,如“their”“there”和“they're”。
- 單複數一致錯誤:句子中單數和複數名詞及動詞搭配錯誤。
未來目標
使用更大的模型,補充模型遺漏的語法案例,採用更好、更大的數據集。
📦 安裝指南
文檔未提供相關安裝步驟,故跳過此章節。
💻 使用示例
基礎用法
卡倫應一次處理一個段落或一段文本。使用時,需按照以下格式輸入:
<|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
注意在實際文本前加上提示語“Edit the following text for spelling and grammar mistakes:”,這樣卡倫就不會對文本進行多餘的討論。
高級用法
以下是一個使用示例及不同版本的輸出: 輸入文本:
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)
嚴格版輸出:
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)
創意版輸出:
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)
🔧 技術細節
訓練方式
卡倫V2是在虛構/非虛構的美式英語文本上進行反向訓練的,這些文本中的錯誤是由另一個Llama模型(Darth Karen)和Python腳本故意插入的。
模型侷限性
經過大概10個不同版本的迭代和改進,當前模型表現尚可,但仍偶爾會遺漏一些語法錯誤(這些錯誤往往存在爭議)。這些侷限性似乎與模型的70億參數有關,參數規模可能不足以讓模型精細理解輸入文本的各種細微差別。這與我的其他發現相符——Mistral模型在生成文本方面表現出色,但在理解方面不夠完美,同樣與70億參數有關。
📄 許可證
本項目使用Llama2許可證。
推薦設置
- 溫度(Temperature):0.7
- 核採樣概率(top_p):0.1
- 採樣數量(top_k):40
- 重複懲罰(repetition penalty):1.18
另外,卡倫也可用於聊天。但如果在對話中輸入的文本較長,她可能會將你的消息理解為需要校對幫助,而不是簡單的閒聊。
總結
創建一個不改變文本風格的模型是本項目的目標。通常,大語言模型(LLM)在編輯文本時,即使文本本身沒問題,也會嘗試重寫。對於這樣一個小模型來說,要在修正文本(且不改變風格)和逐字複製之間找到平衡,是相當具有挑戰性的。嚴格版模型假定你已經是一位優秀的作家,清楚自己的每一個用詞。



