Karen TheEditor V2 CREATIVE Mistral 7B

🚀 Karen is an editor for your text. (v.2) CREATIVE edition

Karen is a text editor that can rectify grammatical and spelling errors in US English without altering the text style.

✨ Features

• Two Versions: There are two versions of Karen V2. The Strict version tries not to make too many changes to the original text, mostly fixing grammar and spelling. The Creative version may suggest slight contextual improvements or rephrasing where necessary.
• Grammar and Spelling Fix: Karen's primary goal is to rectify grammatical and spelling errors in US English without altering the style of the text. It can identify and correct common ESL errors, including verb tense errors, subject - verb agreement issues, incorrect use of articles, prepositions, word order, pluralization, pronoun errors, double negatives, modal verbs, confusing similar words, and lack of plural/singular agreement.

📦 Installation

No installation information is provided in the original document.

💻 Usage Examples

Basic Usage

Karen should be used by submitting a paragraph or block of text at a time. The input format follows ChatML:

<|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

Note the pretext: Edit the following text for spelling and grammar mistakes: before the actual text. This way Karen wouldn't start talking ABOUT the text.

Example Input and Output

Input:

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.

Output STRICT:

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.

Output CREATIVE:

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.

📚 Documentation

Info

Karen, Version 2, uses a completely different data set and base model than the previous Karen.

Goals

Karen's primary goal is to rectify grammatical and spelling errors in US English without altering the style of the text. She is adept at identifying and correcting common ESL errors, including:

• Verb Tense Errors: Incorrect use of verb tenses, such as using present tense when past tense is required and vice versa; confusion between continuous and simple tenses.
• Subject - Verb Agreement: Lack of agreement between the subject and verb in number, e.g., using a singular verb with a plural subject or vice versa.
• Articles (a, an, the): Incorrect use or omission of articles, such as using "a" instead of "an" or vice versa; overuse or omission of the definite article "the."
• Prepositions: Misuse of prepositions, such as using "in" instead of "on" or "at," or omitting prepositions where they are needed.
• Word Order: Incorrect word order in sentences, especially in questions and negative sentences; misplacement of adverbs or adjectives.
• Pluralization: Incorrect plural forms of nouns, such as failing to add "-s" or "-es" when necessary.
• Pronoun Errors: Confusion between subject and object pronouns; incorrect use of possessive pronouns.
• Double Negatives: Using double negatives, which is grammatically incorrect in standard English.
• Modal Verbs: Misuse of modal verbs like can, could, will, would, should, etc.
• Confusing Similar Words: Confusing words that sound similar but have different meanings and spellings (e.g., "their," "there," and "they're").
• Lack of Plural/Singular Agreement: Mistakes in matching singular and plural nouns and verbs in a sentence.

Future Goals

Use a bigger model, add grammar cases that the model misses, and use better and larger datasets.

🔧 Technical Details

It was reversely trained on fict/non - fiction US text where errors were intentionally inserted by another Llama model (Darth Karen) and Python script.

The current model has some limitations related to the 7B parameters. The size isn't sufficient to have a fine - grained understanding of various nuances of the input. The Mistral model performs quite well when generating its own text, but its comprehension is less than perfect, again related to only 7B parameters.

📄 License

The license of this project is llama2.