rixty/SillyTavern
1
0
Fork 0
mirror of https://github.com/SillyTavern/SillyTavern.git synced 2025-06-05 21:59:27 +02:00
Code Issues Packages Projects Releases Wiki Activity

@1.1.0

Browse Source 
1)NovelAI support
2)Changing your character name
3)Repetition Penalty has been moved to the main settings
4)Added Pro settings (Anchors Order)
5)Max Context and Amount Gen have been added to the Pro Settings
6)Editing messages
7)New backgrounds
This commit is contained in:
Ash
2023-01-08 17:18:10 +04:00
parent a9c0d50da2
commit fbf2d5fc00
28 changed files with 1196 additions and 105 deletions
Download Patch File Download Diff File Expand all files Collapse all files

BIN
public/notes/1.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 6.5 KiB

BIN
public/notes/2.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 25 KiB

15
public/notes/4.html
View File

@@ -1,6 +1,6 @@
<html>
<head>
<title>Preset settings</title>
<title>KoboldAI Settings</title>
<link rel="stylesheet" href="/css/notes.css">
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
@@ -8,16 +8,21 @@
<body>
<div id="main">
<div id="content">
<h2>Preset settings</h2>
<h2>KoboldAI Settings</h2>
<p>Standard KoboldAI settings files are used here. To add your own settings, simply add the file .settings in TavernAI\public\KoboldAI Settings
<br><br>Important: Temporarily, at the moment, the context will always be 2048 tokens, regardless of any settings.
</p>
<h3>Temperature</h3>
<p>Value from 0.1 to 2.0. Lower value - the answers are more logical, but less creative. Higher value - the answers are more creative, but less logical.</p>
<h3>Repetition penalty</h3>
<p>Repetition penalty is responsible for the penalty of repeated words. If the character is fixated on something or repeats the same phrase, then increasing this parameter will fix it. It is not recommended to increase this parameter too much for the chat format, as it may break this format. The standard value for chat is approximately 1.0 - 1.05</p>
<h3>Repetition penalty range</h3>
<p>The range of influence of Repetition penalty in tokens.</p><br>
<h2>Pro settings</h2>
<h3>Amount generation</h3>
<p>The maximum amount of tokens that a AI will generate to respond. One word is approximately 3-4 tokens. The larger the parameter value, the longer the generation time takes.</p>
<h3>User Avatar</h3>
<p>Images can be added in TavernAI\public\User Avatars</p>
<h3>Context size</h3>
<p>How much will the AI remember. Context size also affects the speed of generation.<br><br>
<u>Important</u>: The settings of Context size in TavernAI GUI override any other settings for KoboldAI(from KoboldAI GUI and from preset files)</p>
</div>
</div>
</body>

28
public/notes/6.html Normal file
View File

@@ -0,0 +1,28 @@
<html>
<head>
<title>NovelAI api key</title>
<link rel="stylesheet" href="/css/notes.css">
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
</head>
<body>
<div id="main">
<div id="content">
<h2>Finding your NAI API key</h2>
<h4>To get a NovelAI API key, follow these instructions:</h4>
1. Login to NovelAI through the website.<br><br>
2. Create a new story, or open an existing story.<br><br>
3. Open the Network Tools on your web browser. (For Chrome or Firefox, you do this by pressing Ctrl+Shift+I, then switching to the Network tab.)<br><br>
4. Generate something. You should see two requests to api.novelai.net/ai/generate-stream, which might look something like this:</p>
<img src="1.png"><br><br>
5. Select the second request, then in the Headers tab of the inspection panel, scroll down to the very bottom. Look for a header called Authorization:<br><br>
<img src="2.png"><br><br>
The long string (after "Bearer", not including it) is your API key.
</div>
</div>
</body>
</html>

23
public/notes/7.html Normal file
View File

@@ -0,0 +1,23 @@
<html>
<head>
<title>NovelAI settings</title>
<link rel="stylesheet" href="/css/notes.css">
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
</head>
<body>
<div id="main">
<div id="content">
<h2>NovelAI settings</h2>
<p>The files with the settings are here (TavernAI\public\NovelAI Settings) You also can add own settings files.
</p>
<h3>Temperature</h3>
<p>Value from 0.1 to 2.0. Lower value - the answers are more logical, but less creative. Higher value - the answers are more creative, but less logical.</p>
<h3>Repetition penalty</h3>
<p>Repetition penalty is responsible for the penalty of repeated words. If the character is fixated on something or repeats the same phrase, then increasing this parameter will fix it. It is not recommended to increase this parameter too much for the chat format, as it may break this format. The standard value for chat is approximately 1.0 - 1.05</p>
<h3>Repetition penalty range</h3>
<p>The range of influence of Repetition penalty in tokens.</p>
</div>
</div>
</body>
</html>

16
public/notes/8.html Normal file
View File

@@ -0,0 +1,16 @@
<html>
<head>
<title>NovelAI Models</title>
<link rel="stylesheet" href="/css/notes.css">
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
</head>
<body>
<div id="main">
<div id="content">
<h2>NovelAI Models</h2>
<h4>If your subscribe tier is Paper, Tablet or Scroll use only Euterpe model otherwise you can not get an answer from NovelAI api.</h4>
</div>
</div>
</body>
</html>

20
public/notes/9.html Normal file
View File

@@ -0,0 +1,20 @@
<html>
<head>
<title>Anchors</title>
<link rel="stylesheet" href="/css/notes.css">
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
</head>
<body>
<div id="main">
<div id="content">
<h2>Anchors</h2>
<h4>Anchors are used to increase the length of messages. There are two types of anchors: Character Anchor and Style Anchor</h4>
<p><u>Character Anchor</u> - affects the character played by the AI by motivating him to write longer messages. Looks like [Alexa talks a lot with descriptions]</p>
<p><u>Style Anchor</u> - affects all AI model, motivating AI to write longer messages. Looks like [Writing style: very long messages]</p>
<hr style="opacity: 0.6;"><p>The order of anchors sets the location of anchors in the promt, the first anchor in the order is much higher and has less influence than the one that follows it.</p>
<p>To disable anchors, you just need to remove the checkboxes.</p>
</div>
</div>
</body>
</html>