🚀 凱倫:文本編輯利器(v.2)嚴格版
凱倫宛如文本世界的專業編輯,致力於修正文本中的語法和拼寫錯誤,同時完美保留原文風格。在處理美國英語文本時,她能精準識別並糾正各類常見錯誤,為你的寫作保駕護航。
🚀 快速開始
版本說明
凱倫V2有兩個版本:
- 嚴格版:此版本儘量不改動原文,主要修復語法和拼寫錯誤,默認你清楚自己的寫作意圖。
- 創意版:點擊此處查看。該版本可能會根據需要提出輕微的上下文改進或改寫建議,就像小酌一杯紅酒後的凱倫,更具創意。
使用方式
每次提交一個段落或一段文本進行處理。使用時需注意在實際文本前加上提示語:Edit the following text for spelling and grammar mistakes: 這樣凱倫就不會對文本進行額外解讀。
推薦設置
- 溫度(Temperature):0.7
- 核採樣概率(top_p):0.1
- 前k採樣(top_k):40
- 重複懲罰(repetition penalty):1.18
凱倫也可用於聊天,但如果文本較長,她可能會將你的消息視為需要校對的內容,而非普通閒聊。
✨ 主要特性
核心功能
凱倫的主要目標是糾正美國英語中的語法和拼寫錯誤,同時保持文本風格不變。她擅長識別和糾正常見的英語作為第二語言(ESL)錯誤,具體包括:
- 動詞時態錯誤:如該用過去時態卻用了現在時態,反之亦然;混淆進行時態和一般時態。
- 主謂一致錯誤:主語和謂語在數上不一致,例如用單數動詞搭配複數主語,或反之。
- 冠詞使用錯誤:錯誤使用或遺漏冠詞,如用“a”代替“an”,反之亦然;過度使用或遺漏定冠詞“the”。
- 介詞使用錯誤:介詞使用不當,如用“in”代替“on”或“at”,或在需要介詞的地方遺漏介詞。
- 詞序錯誤:句子中的詞序錯誤,特別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;物主代詞使用錯誤。
- 雙重否定錯誤: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:情態動詞如can、could、will、would、should等使用不當。
- 易混淆詞彙錯誤:混淆發音相似但含義和拼寫不同的單詞(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。
效果展示
以下是使用凱倫編輯前後的文本對比:
原文:
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評分: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評分: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評分:83)
📦 安裝指南
文檔未提及安裝相關內容,故跳過此章節。
💻 使用示例
文檔未提供代碼示例,故跳過此章節。
📚 詳細文檔
模型信息
凱倫V2與之前的版本使用了完全不同的數據集和基礎模型。
訓練方式
該模型通過反向訓練,使用另一個Llama模型(Darth Karen)和Python腳本故意在虛構/非虛構美國文本中插入錯誤進行訓練。
未來目標
- 使用更大的模型。
- 增加模型遺漏的語法案例。
- 使用更好、更大的數據集。
總結
經過大約10個不同版本的迭代和改進,當前模型表現良好,但偶爾會出現語法錯誤(且這些錯誤往往存在爭議)。模型的侷限性似乎與7B參數有關,參數規模不足以對輸入的各種細微差別進行精細理解。這與我的其他發現一致——Mistral模型在生成自己的文本時表現相當不錯,但理解能力並不完美,同樣與7B參數有關。
創建這個模型的目標是在不改變文本風格的前提下修正語法和拼寫錯誤。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)和逐字複製文本之間找到正確的平衡是相當具有挑戰性的。嚴格版模型假設你已經是一位優秀的作家,不需要過多指導,並且你寫下的每個字都有其用意。
評估結果
詳細的評估結果可在此處查看。
指標 |
值 |
平均值 |
59.13 |
AI2推理挑戰(25-shot) |
59.56 |
HellaSwag(10-shot) |
81.79 |
MMLU(5-shot) |
59.56 |
TruthfulQA(0-shot) |
49.36 |
Winogrande(5-shot) |
74.35 |
GSM8k(5-shot) |
30.17 |
🔧 技術細節
文檔未提供足夠的技術實現細節,故跳過此章節。
📄 許可證
本項目使用Llama2許可證。