GhostGate commited on
Commit
8757923
·
verified ·
1 Parent(s): 0e4bfae

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +14 -0
README.md CHANGED
@@ -100,19 +100,33 @@ This is a very basic representation of how to build a character, someone like Da
100
  As models are trained on a large amount of code and structured data, it is easier to use MD format when describing your character. Let’s take our David example and transform the format.
101
 
102
  **Name:** David Willson
 
103
  **Sex:** Male
 
104
  **Age:** 20
 
105
  **Height:** 6'1
 
106
  **Occupation:** Computer Science Student at local university
 
107
  **Appearance:** Short dark hair, green eyes, lanky, wears jeans and a black t-shirt
 
108
  **Personality:** Jokester, easily excited, always in a good mood, sees the bright side in everything
 
109
  **Hobbies:** Playing video games, Hiking
 
110
  **Weakness:** David is terrible at time management, procrastination
 
111
  **Likes:** Sodas, pets, video games, his friends
 
112
  **Dislikes:** Complaining, rude people, broccoli, stress
 
113
  **Fears:** David fears that he will fail to graduate and disappoint his parents
 
114
  **Goals:** Graduate university
 
115
  **Motivation:** Make his parents proud
116
 
117
 
 
118
  This should be quite easy to understand for any LLM. It structures David’s attributes easily and LLM’s, no matter the parameter count, can easily follow, thanks to the massive amount of code they ingested.
 
100
  As models are trained on a large amount of code and structured data, it is easier to use MD format when describing your character. Let’s take our David example and transform the format.
101
 
102
  **Name:** David Willson
103
+
104
  **Sex:** Male
105
+
106
  **Age:** 20
107
+
108
  **Height:** 6'1
109
+
110
  **Occupation:** Computer Science Student at local university
111
+
112
  **Appearance:** Short dark hair, green eyes, lanky, wears jeans and a black t-shirt
113
+
114
  **Personality:** Jokester, easily excited, always in a good mood, sees the bright side in everything
115
+
116
  **Hobbies:** Playing video games, Hiking
117
+
118
  **Weakness:** David is terrible at time management, procrastination
119
+
120
  **Likes:** Sodas, pets, video games, his friends
121
+
122
  **Dislikes:** Complaining, rude people, broccoli, stress
123
+
124
  **Fears:** David fears that he will fail to graduate and disappoint his parents
125
+
126
  **Goals:** Graduate university
127
+
128
  **Motivation:** Make his parents proud
129
 
130
 
131
+
132
  This should be quite easy to understand for any LLM. It structures David’s attributes easily and LLM’s, no matter the parameter count, can easily follow, thanks to the massive amount of code they ingested.