tags:
- llm
- llama
- spellcheck
- grammar
Karen is a grammar and spell check editor for your text. (v.2)
Ah, Karen, a true peach among grammatical cucumbers! She yearns to rectify the missteps and linguistic tangles that infest your horribly written fiction. Yet, unlike those ChatGPT kaboodles that morph into self-absorbed, constipated gurus of self-help style, Karen remains steadfastly grounded in grammatical wisdom but respectfull of your style.
Info
Karen, Version 2, uses a completely different data set and base model than the previous Karen.
Goals
Karen's goal is to fix grammatical and spelling errors with as light a change to the style as possible. It's tuned to catch most typical ESL errors.
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
Add more grammar error cases. Better datasets. Use larger datasets.
Training
It was reversely trained on fictional passages where errors were intentionally inserted by another Llama model and Python script.
Usage
It should be used by submitting a paragraph or block of text at a time.
Model uses 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.
Recomended settings
-Temperature: 0.7 -top_p: 0.1 -top_k: 40 -repetition penalty: 1.18
Karen could also be employed in the instruction/chat, but the minute you ran a longer sentence she would assume you were proofreading.
Example:
Edit the following text for spelling and grammar mistakes: Each of candidates’ names were written on pieces of paper folded in half and placed in the appropriate box.
Output:
Each candidate's name was written on a piece of paper, folded in half, and placed in an appropriate box.