File size: 3,427 Bytes
c41237c
 
 
 
 
 
 
accd354
 
 
 
 
 
 
 
 
 
cbd98ae
 
 
 
 
7825f14
 
 
cbd98ae
c759a32
8323eee
cbd98ae
428bc25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ce6ba84
428bc25
619f1c3
ce6ba84
619f1c3
307db9a
 
 
cbd98ae
 
 
 
 
 
 
 
 
83653d8
428bc25
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
---
tags:
- llm
- llama
- spellcheck
- grammar
---

<!-- header start -->
<div style="width: 100%;">
    <img src="https://media.tenor.com/frGCmLDFbkMAAAAC/karen-ok.gif" alt="FPHam's Karen" style="width: 30%; min-width: 200px; display: block; margin: auto;">
</div>
<div style="display: flex; flex-direction: column; align-items: center;">
        <p><a href="https://ko-fi.com/Q5Q5MOB4M">Buy Karen Ko-fi</a></p>
    </div>
<!-- header end -->

# 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 V2 uses completely different dataset and base model than the previous Karen

# Goals
Karen's goals are fixing grammar and spelling errors with as lite changes 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 dataset, use larger dataset

# Training
It was reverse trained on fiction paragraphs where errors were deliberately introduced 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. It works without it, but it was trained with this pretext.

Karen can be used for instruct chat as well - but the moment you use longer paragraph she will assume you want to correct it.