ParasiticRogue commited on
Commit
cacfc63
·
verified ·
1 Parent(s): 33f28c7

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +13 -0
README.md CHANGED
@@ -103,26 +103,39 @@ Lets get the obvious thing out of the way. Character Cards are basically persona
103
  ### 2-2 What are the different styles of Character Cards?
104
 
105
  Making a card isn't exactly a solved science, and the way its prompted could vary the outcome between different model brands and model sizes. However, there are a few that are popular among the community that have gained traction.
 
106
  One way to approach it is a simply writing out the character's persona like you would in a novel/book, using natural prose to describe their background and appearance. Though this method would require a deft hand/mind to make sure it flows well and doesn't repeat too much with specific keywords, and might be a bit harder compered to some of the other styles if you are just starting out. More useful for pure writers, probably.
 
107
  Another is doing a list format, where every feature is placed out categorically and sufficiently. There are different ways of doing this as well, like markdown, wiki style, or the community made W++, just to name a few.
 
108
  Some use parentheses or brackets to enclose each section, some use dashes for separate listings, some bold sections with hashes or double asterisks, or some none of the above.
 
109
  I haven't found which one is objectively the best when it comes to a specific format, although W++ is probably the worst of the bunch when it comes to stabilization, with Wiki Style taking second worse just because of it being bloat dumped from said wiki. There could be a myriad of reasons why W++ might not be considered as much anymore, but my best guess is, since the format is non-standard in most model's training data, it has less to pull from in its reasoning.
 
110
  My current recommendation is just to use some mixture of lists and regular prose, with a traditional list when it comes to appearance and traits, and using normal writing for background and speech. Though you should be mindful of what perspective you prompt the card beforehand.
111
 
112
  ### 2-3 What writing perspectives should I consider before making a card?
113
 
114
  This one is probably more definitive and easier to wrap your head around then choosing a specific listing style. First, we must discuss what perspective to write your card and example messages for the bot in: I, You, They. This demonstrates perspective the card is written in - First-person, Second-Person, Third-person - and will have noticeable effects on the bot's output. Even cards the are purely list based will still incorporate some form of character perspective, and some are better then others for certain tasks.
 
115
  "I" format has the entire card written from the characters perspective, listing things out as if they themselves made it. Useful if you want your bots to act slightly more individualized for one-on-one chats, but requires more thought put into the word choices in order to make sure it is accurate to the way they talk/interact. Most common way people talk online. Keywords: I, my, mine.
 
116
  "You" format is telling the bot what they are from your perspective, and is typically the format used in system prompts and technical AI training, but has less outside example data like with "I" in chats/writing, and is less personable as well. Keywords: You, your, you're.
 
117
  "They" format is the birds-eye view approach commonly found in storytelling. Lots of novel examples in training data. Best for creative writers, and works better in group chats to avoid confusion for the AI on who is/was talking. Keywords: They, their, she/he/its.
 
118
  In essence, LLMs are prediction based machines, and the way words are chosen or structured will determine the next probable outcome. Do you want a personable one-on-one chat with your bots? Try "I" as your template. Want a creative writer that will keep track of multiple characters? Use "They" as your format. Want the worst of both worlds, but might be better at technical LLM jobs? Choose "You" format.
 
119
  This reasoning also carries over to the chats themselves and how you interact with the bots, though you'd have to use a mixture with "You" format specifically, and that's another reason it might not be as good comparatively speaking, since it will be using two or more styles at once. But there is more to consider still, such as whether to use quotes or asterisks.
120
 
121
  ### 2-4 Should I use quotes or asterisks as the defining separator in the chat?
122
 
123
  Now we must move on to another aspect to consider before creating a character card, and the way you warp the words inside: To use "quotes with speech" and plain text with actions, or plain text with speech and *asterisks with actions*. These two formats are fundamentally opposed with one another, and will draw from separate sources in the LLMs training data, however much that is, due to their predictive nature.
 
124
  Quote format is the dominant storytelling format, and will have better prose on average. If your character or archetype originated from literature, or is heavily used in said literature, then wrapping the dialogue in quotes will get you better results.
 
125
  Asterisk format is much more niche in comparison, mostly used in RP servers - and not all RP servers will opt for this format either - and brief text chats. If you want your experience to feel more like a texting session, then this one might be for you.
 
126
  Mixing these two - "Like so" *I said* - however, is not advised, as it will eat up extra tokens for no real benefit. No formats that I know of use this in typical training data, and if it does, is extremely rare. Only use if you want to waste tokens/context on word flair.
127
 
128
  ### 2-5 What combination would you recommend?
 
103
  ### 2-2 What are the different styles of Character Cards?
104
 
105
  Making a card isn't exactly a solved science, and the way its prompted could vary the outcome between different model brands and model sizes. However, there are a few that are popular among the community that have gained traction.
106
+
107
  One way to approach it is a simply writing out the character's persona like you would in a novel/book, using natural prose to describe their background and appearance. Though this method would require a deft hand/mind to make sure it flows well and doesn't repeat too much with specific keywords, and might be a bit harder compered to some of the other styles if you are just starting out. More useful for pure writers, probably.
108
+
109
  Another is doing a list format, where every feature is placed out categorically and sufficiently. There are different ways of doing this as well, like markdown, wiki style, or the community made W++, just to name a few.
110
+
111
  Some use parentheses or brackets to enclose each section, some use dashes for separate listings, some bold sections with hashes or double asterisks, or some none of the above.
112
+
113
  I haven't found which one is objectively the best when it comes to a specific format, although W++ is probably the worst of the bunch when it comes to stabilization, with Wiki Style taking second worse just because of it being bloat dumped from said wiki. There could be a myriad of reasons why W++ might not be considered as much anymore, but my best guess is, since the format is non-standard in most model's training data, it has less to pull from in its reasoning.
114
+
115
  My current recommendation is just to use some mixture of lists and regular prose, with a traditional list when it comes to appearance and traits, and using normal writing for background and speech. Though you should be mindful of what perspective you prompt the card beforehand.
116
 
117
  ### 2-3 What writing perspectives should I consider before making a card?
118
 
119
  This one is probably more definitive and easier to wrap your head around then choosing a specific listing style. First, we must discuss what perspective to write your card and example messages for the bot in: I, You, They. This demonstrates perspective the card is written in - First-person, Second-Person, Third-person - and will have noticeable effects on the bot's output. Even cards the are purely list based will still incorporate some form of character perspective, and some are better then others for certain tasks.
120
+
121
  "I" format has the entire card written from the characters perspective, listing things out as if they themselves made it. Useful if you want your bots to act slightly more individualized for one-on-one chats, but requires more thought put into the word choices in order to make sure it is accurate to the way they talk/interact. Most common way people talk online. Keywords: I, my, mine.
122
+
123
  "You" format is telling the bot what they are from your perspective, and is typically the format used in system prompts and technical AI training, but has less outside example data like with "I" in chats/writing, and is less personable as well. Keywords: You, your, you're.
124
+
125
  "They" format is the birds-eye view approach commonly found in storytelling. Lots of novel examples in training data. Best for creative writers, and works better in group chats to avoid confusion for the AI on who is/was talking. Keywords: They, their, she/he/its.
126
+
127
  In essence, LLMs are prediction based machines, and the way words are chosen or structured will determine the next probable outcome. Do you want a personable one-on-one chat with your bots? Try "I" as your template. Want a creative writer that will keep track of multiple characters? Use "They" as your format. Want the worst of both worlds, but might be better at technical LLM jobs? Choose "You" format.
128
+
129
  This reasoning also carries over to the chats themselves and how you interact with the bots, though you'd have to use a mixture with "You" format specifically, and that's another reason it might not be as good comparatively speaking, since it will be using two or more styles at once. But there is more to consider still, such as whether to use quotes or asterisks.
130
 
131
  ### 2-4 Should I use quotes or asterisks as the defining separator in the chat?
132
 
133
  Now we must move on to another aspect to consider before creating a character card, and the way you warp the words inside: To use "quotes with speech" and plain text with actions, or plain text with speech and *asterisks with actions*. These two formats are fundamentally opposed with one another, and will draw from separate sources in the LLMs training data, however much that is, due to their predictive nature.
134
+
135
  Quote format is the dominant storytelling format, and will have better prose on average. If your character or archetype originated from literature, or is heavily used in said literature, then wrapping the dialogue in quotes will get you better results.
136
+
137
  Asterisk format is much more niche in comparison, mostly used in RP servers - and not all RP servers will opt for this format either - and brief text chats. If you want your experience to feel more like a texting session, then this one might be for you.
138
+
139
  Mixing these two - "Like so" *I said* - however, is not advised, as it will eat up extra tokens for no real benefit. No formats that I know of use this in typical training data, and if it does, is extremely rare. Only use if you want to waste tokens/context on word flair.
140
 
141
  ### 2-5 What combination would you recommend?