rixty
/
KoboldAI-Client
mirror of https://github.com/KoboldAI/KoboldAI-Client.git
1
1
Fork 0
Code Issues Projects Releases Wiki Activity
KoboldAI-Client/gensettings.py

416 lines
10 KiB
Python
Raw Normal View History

Reordering Settings More settings reordering so similar settings are on the same rows now that we have more settings for the repetition penalty. Amount to generate is now top left so some muscle memory may be lost with the temp. But the settings that control AI randomness are on the same row now, and repetition related settings are next to each other as well.
2022-01-25 06:10:39 +01:00
gensettingstf = [
{
"uitype": "slider",
"unit": "int",
"label": "Amount to Generate",
"id": "setoutput",
"min": 16,
"max": 512,
"step": 2,
"default": 80,
"tooltip": "Number of tokens the AI should generate. Higher numbers will take longer to generate."
},
{
Settings menu modularized. Help text added to settings items. Settings now saved to client file when changed. Separated transformers settings and InferKit settings. Reorganized model select list.
2021-05-07 20:32:10 +02:00
"uitype": "slider",
"unit": "float",
"label": "Temperature",
"id": "settemp",
"min": 0.1,
"max": 2.0,
Safer defaults and more flexibility There have been a lot of reports from newer users who experience AI breakdown because not all models properly handle 2048 max tokens. 1024 is the only value that all models support and was the original value KoboldAI used. This commit reverts the decision to increase this to 2048, any existing configurations are not effected. Users who wish to increase the max tokens can do so themselves. Most models handle up to 1900 well (The GPT2 models are excluded), for many you can go all the way. (It is currently not yet known why some finetunes cause a decrease in maxtoken support, In addition this commit contains a request for more consistent slider behavior, allowing the sliders to be changed at 0.01 intervals instead of some sliders being capped to 0.05.
2022-07-03 15:07:54 +02:00
"step": 0.01,
Random Story Generator Add the Random Story Generator and more userfriendly defaults
2021-08-19 12:54:44 +02:00
"default": 0.5,
Settings menu modularized. Help text added to settings items. Settings now saved to client file when changed. Separated transformers settings and InferKit settings. Reorganized model select list.
2021-05-07 20:32:10 +02:00
"tooltip": "Randomness of sampling. High values can increase creativity but may make text less sensible. Lower values will make text more predictable but can become repetitious."
},
{
"uitype": "slider",
"unit": "float",
"label": "Top p Sampling",
"id": "settopp",
top_k and tfs support by Frogging101 Adds top_k and tfs support, also fixes a SocketIO error.
2021-08-19 14:47:57 +02:00
"min": 0.0,
Settings menu modularized. Help text added to settings items. Settings now saved to client file when changed. Separated transformers settings and InferKit settings. Reorganized model select list.
2021-05-07 20:32:10 +02:00
"max": 1.0,
Safer defaults and more flexibility There have been a lot of reports from newer users who experience AI breakdown because not all models properly handle 2048 max tokens. 1024 is the only value that all models support and was the original value KoboldAI used. This commit reverts the decision to increase this to 2048, any existing configurations are not effected. Users who wish to increase the max tokens can do so themselves. Most models handle up to 1900 well (The GPT2 models are excluded), for many you can go all the way. (It is currently not yet known why some finetunes cause a decrease in maxtoken support, In addition this commit contains a request for more consistent slider behavior, allowing the sliders to be changed at 0.01 intervals instead of some sliders being capped to 0.05.
2022-07-03 15:07:54 +02:00
"step": 0.01,
Random Story Generator Add the Random Story Generator and more userfriendly defaults
2021-08-19 12:54:44 +02:00
"default": 0.9,
Various Fixes Various Fixes, mostly to make the UI play a little nicer in the new edit mode. Also reverted and optimized some of the setting stuff.
2021-08-24 01:18:09 +02:00
"tooltip": "Used to discard unlikely text in the sampling process. Lower values will make text more predictable but can become repetitious. (Put this value on 1 to disable its effect)"
top_k and tfs support by Frogging101 Adds top_k and tfs support, also fixes a SocketIO error.
2021-08-19 14:47:57 +02:00
},
{
"uitype": "slider",
"unit": "int",
"label": "Top k Sampling",
"id": "settopk",
"min": 0,
"max": 100,
"step": 1,
"default": 0,
Various Fixes Various Fixes, mostly to make the UI play a little nicer in the new edit mode. Also reverted and optimized some of the setting stuff.
2021-08-24 01:18:09 +02:00
"tooltip": "Alternative sampling method, can be combined with top_p. (Put this value on 0 to disable its effect)"
top_k and tfs support by Frogging101 Adds top_k and tfs support, also fixes a SocketIO error.
2021-08-19 14:47:57 +02:00
},
{
"uitype": "slider",
"unit": "float",
"label": "Tail-free Sampling",
"id": "settfs",
"min": 0.0,
"max": 1.0,
Safer defaults and more flexibility There have been a lot of reports from newer users who experience AI breakdown because not all models properly handle 2048 max tokens. 1024 is the only value that all models support and was the original value KoboldAI used. This commit reverts the decision to increase this to 2048, any existing configurations are not effected. Users who wish to increase the max tokens can do so themselves. Most models handle up to 1900 well (The GPT2 models are excluded), for many you can go all the way. (It is currently not yet known why some finetunes cause a decrease in maxtoken support, In addition this commit contains a request for more consistent slider behavior, allowing the sliders to be changed at 0.01 intervals instead of some sliders being capped to 0.05.
2022-07-03 15:07:54 +02:00
"step": 0.01,
Typical sampling
2022-03-27 22:25:50 +02:00
"default": 1.0,
Various Fixes Various Fixes, mostly to make the UI play a little nicer in the new edit mode. Also reverted and optimized some of the setting stuff.
2021-08-24 01:18:09 +02:00
"tooltip": "Alternative sampling method; it is recommended to disable top_p and top_k (set top_p to 1 and top_k to 0) if using this. 0.95 is thought to be a good value. (Put this value on 1 to disable its effect)"
Settings menu modularized. Help text added to settings items. Settings now saved to client file when changed. Separated transformers settings and InferKit settings. Reorganized model select list.
2021-05-07 20:32:10 +02:00
},
{
"uitype": "slider",
"unit": "float",
Typical sampling
2022-03-27 22:25:50 +02:00
"label": "Typical Sampling",
"id": "settypical",
"min": 0.0,
"max": 1.0,
Safer defaults and more flexibility There have been a lot of reports from newer users who experience AI breakdown because not all models properly handle 2048 max tokens. 1024 is the only value that all models support and was the original value KoboldAI used. This commit reverts the decision to increase this to 2048, any existing configurations are not effected. Users who wish to increase the max tokens can do so themselves. Most models handle up to 1900 well (The GPT2 models are excluded), for many you can go all the way. (It is currently not yet known why some finetunes cause a decrease in maxtoken support, In addition this commit contains a request for more consistent slider behavior, allowing the sliders to be changed at 0.01 intervals instead of some sliders being capped to 0.05.
2022-07-03 15:07:54 +02:00
"step": 0.01,
Typical sampling
2022-03-27 22:25:50 +02:00
"default": 1.0,
"tooltip": "Alternative sampling method described in the paper \"Typical Decoding for Natural Language Generation\" (10.48550/ARXIV.2202.00666). The paper suggests 0.2 as a good value for this setting. Set this setting to 1 to disable its effect."
},
{
"uitype": "slider",
"unit": "float",
Top-A sampling
2022-06-11 04:28:20 +02:00
"label": "Top a Sampling",
"id": "settopa",
"min": 0.0,
"max": 1.0,
"step": 0.01,
"default": 0.0,
"tooltip": "Alternative sampling method that reduces the randomness of the AI whenever the probability of one token is much higher than all the others. Higher values have a stronger effect. Set this setting to 0 to disable its effect."
},
{
"uitype": "slider",
"unit": "float",
Settings menu modularized. Help text added to settings items. Settings now saved to client file when changed. Separated transformers settings and InferKit settings. Reorganized model select list.
2021-05-07 20:32:10 +02:00
"label": "Repetition Penalty",
"id": "setreppen",
"min": 1.0,
Allow Repetition Penalty up to 3 A user expressed positive feedback when trying higher than 2 repetition penalty on some models, lets allow people the freedom to do so. If there is a demonstrable benefit to running higher than 3 I am open to raising it again.
2021-12-28 03:22:14 +01:00
"max": 3.0,
Better Repetition Penalty Slider Allow users more control since 6B is sensitive
2021-11-29 08:28:51 +01:00
"step": 0.01,
Random Story Generator Add the Random Story Generator and more userfriendly defaults
2021-08-19 12:54:44 +02:00
"default": 1.1,
Allow Repetition Penalty up to 3 A user expressed positive feedback when trying higher than 2 repetition penalty on some models, lets allow people the freedom to do so. If there is a demonstrable benefit to running higher than 3 I am open to raising it again.
2021-12-28 03:22:14 +01:00
"tooltip": "Used to penalize words that were already generated or belong to the context (Going over 1.2 breaks 6B models)."
Settings menu modularized. Help text added to settings items. Settings now saved to client file when changed. Separated transformers settings and InferKit settings. Reorganized model select list.
2021-05-07 20:32:10 +02:00
},
{
"uitype": "slider",
"unit": "int",
Repetition penalty slope and range
2022-01-24 21:30:38 +01:00
"label": "Rep Penalty Range",
"id": "setreppenrange",
"min": 0,
"max": 4096,
"step": 4,
"default": 0,
"tooltip": "Repetition penalty range. If set higher than 0, only applies repetition penalty to the last few tokens of your story rather than applying it to the entire story. This slider controls the amount of tokens at the end of your story to apply it to."
},
{
"uitype": "slider",
"unit": "float",
"label": "Rep Penalty Slope",
"id": "setreppenslope",
"min": 0.0,
"max": 10.0,
"step": 0.1,
"default": 0.0,
"tooltip": "Repetition penalty slope. If BOTH this setting and Rep Penalty Range are set higher than 0, will use sigmoid interpolation to apply repetition penalty more strongly on tokens that are closer to the end of your story. This setting controls the tension of the sigmoid curve; higher settings will result in the repetition penalty difference between the start and end of your story being more apparent. Setting this to 1 uses linear interpolation; setting this to 0 disables interpolation."
Settings menu modularized. Help text added to settings items. Settings now saved to client file when changed. Separated transformers settings and InferKit settings. Reorganized model select list.
2021-05-07 20:32:10 +02:00
},
{
"uitype": "slider",
"unit": "int",
"label": "Max Tokens",
"id": "settknmax",
"min": 512,
Various Fixes Various Fixes, mostly to make the UI play a little nicer in the new edit mode. Also reverted and optimized some of the setting stuff.
2021-08-24 01:18:09 +02:00
"max": 2048,
Settings menu modularized. Help text added to settings items. Settings now saved to client file when changed. Separated transformers settings and InferKit settings. Reorganized model select list.
2021-05-07 20:32:10 +02:00
"step": 8,
Random Story Generator Add the Random Story Generator and more userfriendly defaults
2021-08-19 12:54:44 +02:00
"default": 1024,
Reduced default max_length parameter to 512. Added warning about VRAM usage to Max Tokens tooltip.
2021-05-08 01:04:51 +02:00
"tooltip": "Max number of tokens of context to submit to the AI for sampling. Make sure this is higher than Amount to Generate. Higher values increase VRAM/RAM usage."
Added option to generate multiple responses per action. Added ability to import World Info files from AI Dungeon. Added slider for setting World Info scan depth. Added toggle to control whether prompt is submitted each action. Added 'Read Only' mode with no AI to startup. Fixed GPU/CPU choice prompt appearing when GPU isn't an option. Added error handling to generator calls for CUDA OOM message Added generator parameter to only return new text
2021-05-29 11:46:03 +02:00
},
{
"uitype": "slider",
"unit": "int",
"label": "Gens Per Action",
"id": "setnumseq",
"min": 1,
"max": 5,
"step": 1,
"default": 1,
"tooltip": "Number of results to generate per submission. Increases VRAM/RAM usage."
},
{
"uitype": "slider",
"unit": "int",
"label": "W Info Depth",
"id": "setwidepth",
"min": 1,
"max": 5,
"step": 1,
Random Story Generator Add the Random Story Generator and more userfriendly defaults
2021-08-19 12:54:44 +02:00
"default": 3,
Added option to generate multiple responses per action. Added ability to import World Info files from AI Dungeon. Added slider for setting World Info scan depth. Added toggle to control whether prompt is submitted each action. Added 'Read Only' mode with no AI to startup. Fixed GPU/CPU choice prompt appearing when GPU isn't an option. Added error handling to generator calls for CUDA OOM message Added generator parameter to only return new text
2021-05-29 11:46:03 +02:00
"tooltip": "Number of historic actions to scan for W Info keys."
},
Setting Toggles Reordering Bit more alphabetical and a (in my eyes) more logical order of the settings.
2022-01-20 19:23:23 +01:00
{
"uitype": "toggle",
"unit": "bool",
"label": "Auto Save",
"id": "autosave",
"min": 0,
"max": 1,
"step": 1,
"default": 0,
"tooltip": "Whether the game is saved after each action."
},
Added option to generate multiple responses per action. Added ability to import World Info files from AI Dungeon. Added slider for setting World Info scan depth. Added toggle to control whether prompt is submitted each action. Added 'Read Only' mode with no AI to startup. Fixed GPU/CPU choice prompt appearing when GPU isn't an option. Added error handling to generator calls for CUDA OOM message Added generator parameter to only return new text
2021-05-29 11:46:03 +02:00
{
"uitype": "toggle",
"unit": "bool",
"label": "Always Add Prompt",
"id": "setuseprompt",
"min": 0,
"max": 1,
"step": 1,
"default": 1,
"tooltip": "Whether the prompt should be sent in the context of every action."
Chat Mode The Initial commit for Chat Mode, the nickname part of the UI is missing other than that it should be fully functional. To use Chat Mode effectively you first input a small dialogue (Can be around 6 lines 3 of your own inputs and 3 of the character) formatted as Name : it will then automate the actions needed to chat properly. During this mode single line mode is forced on, and Trim Incomplete Sentences is forced off.
2021-12-26 01:51:32 +01:00
},
{
"uitype": "toggle",
"unit": "bool",
Setting Toggles Reordering Bit more alphabetical and a (in my eyes) more logical order of the settings.
2022-01-20 19:23:23 +01:00
"label": "Adventure Mode",
"id": "setadventure",
Chat Mode The Initial commit for Chat Mode, the nickname part of the UI is missing other than that it should be fully functional. To use Chat Mode effectively you first input a small dialogue (Can be around 6 lines 3 of your own inputs and 3 of the character) formatted as Name : it will then automate the actions needed to chat properly. During this mode single line mode is forced on, and Trim Incomplete Sentences is forced off.
2021-12-26 01:51:32 +01:00
"min": 0,
"max": 1,
"step": 1,
"default": 0,
Setting Toggles Reordering Bit more alphabetical and a (in my eyes) more logical order of the settings.
2022-01-20 19:23:23 +01:00
"tooltip": "Turn this on if you are playing a Choose your Adventure model."
Integrated VE_FORBRYDERNE's Adventure Mode + Cleanup Adventure Mode allows you to play this like AID, perfect for Choose your own Adventure models
2021-08-19 13:18:01 +02:00
},
{
"uitype": "toggle",
"unit": "bool",
Setting Toggles Reordering Bit more alphabetical and a (in my eyes) more logical order of the settings.
2022-01-20 19:23:23 +01:00
"label": "Chat Mode",
"id": "setchatmode",
Integrated VE_FORBRYDERNE's Adventure Mode + Cleanup Adventure Mode allows you to play this like AID, perfect for Choose your own Adventure models
2021-08-19 13:18:01 +02:00
"min": 0,
"max": 1,
"step": 1,
"default": 0,
Setting Toggles Reordering Bit more alphabetical and a (in my eyes) more logical order of the settings.
2022-01-20 19:23:23 +01:00
"tooltip": "This mode optimizes KoboldAI for chatting."
Make the dynamic world info scan toggleable
2021-11-03 17:18:48 +01:00
},
{
"uitype": "toggle",
"unit": "bool",
"label": "Dynamic WI Scan",
"id": "setdynamicscan",
"min": 0,
"max": 1,
"step": 1,
"default": 0,
Support for multiple gens per action with dynamic scan
2021-11-17 22:17:59 +01:00
"tooltip": "Scan the AI's output for world info keys as it's generating the output."
No Prompt Gen Allow people to enter a prompt without generating anything by the AI. Combined with the always add prompt this is a very useful feature that allows people to write world information first, and then do a specific action. This mimics the behavior previously seen in AI Dungeon forks where it prompts for world information and then asks an action and can be particularly useful for people who want the prompt to always be part of the generation.
2021-12-16 12:47:44 +01:00
},
{
"uitype": "toggle",
"unit": "bool",
"label": "No Prompt Generation",
"id": "setnopromptgen",
"min": 0,
"max": 1,
"step": 1,
"default": 0,
"tooltip": "When enabled the AI does not generate when you enter the prompt, instead you need to do an action first."
Add Memory box to Random Story dialog and "Random Story Persist"
2021-12-30 05:15:59 +01:00
},
{
"uitype": "toggle",
"unit": "bool",
"label": "Random Story Persist",
"id": "setrngpersist",
"min": 0,
"max": 1,
"step": 1,
"default": 0,
"tooltip": "When enabled, the Memory text box in the Random Story dialog will be prefilled by default with your current story's memory instead of being empty."
Use original TPU backend if possible
2022-01-16 05:31:07 +01:00
},
{
"uitype": "toggle",
"unit": "bool",
"label": "No Genmod",
"id": "setnogenmod",
"min": 0,
"max": 1,
"step": 1,
"default": 0,
Setting Toggles Reordering Bit more alphabetical and a (in my eyes) more logical order of the settings.
2022-01-20 19:23:23 +01:00
"tooltip": "Disables userscript generation modifiers."
Fix for redo with options. Added debug menu
2022-01-24 18:54:44 +01:00
},
{
"uitype": "toggle",
"unit": "bool",
"label": "Debug",
"id": "debug",
"min": 0,
"max": 1,
"step": 1,
"default": 0,
"tooltip": "Show debug info"
Setting Toggles Reordering Bit more alphabetical and a (in my eyes) more logical order of the settings.
2022-01-20 19:23:23 +01:00
}
]
Settings menu modularized. Help text added to settings items. Settings now saved to client file when changed. Separated transformers settings and InferKit settings. Reorganized model select list.
2021-05-07 20:32:10 +02:00
gensettingsik =[{
"uitype": "slider",
"unit": "float",
"label": "Temperature",
"id": "settemp",
"min": 0.1,
"max": 2.0,
"step": 0.05,
Random Story Generator Add the Random Story Generator and more userfriendly defaults
2021-08-19 12:54:44 +02:00
"default": 0.5,
Settings menu modularized. Help text added to settings items. Settings now saved to client file when changed. Separated transformers settings and InferKit settings. Reorganized model select list.
2021-05-07 20:32:10 +02:00
"tooltip": "Randomness of sampling. High values can increase creativity but may make text less sensible. Lower values will make text more predictable but can become repetitious."
},
{
"uitype": "slider",
"unit": "float",
"label": "Top p Sampling",
"id": "settopp",
top_k and tfs support by Frogging101 Adds top_k and tfs support, also fixes a SocketIO error.
2021-08-19 14:47:57 +02:00
"min": 0.0,
Settings menu modularized. Help text added to settings items. Settings now saved to client file when changed. Separated transformers settings and InferKit settings. Reorganized model select list.
2021-05-07 20:32:10 +02:00
"max": 1.0,
"step": 0.05,
Random Story Generator Add the Random Story Generator and more userfriendly defaults
2021-08-19 12:54:44 +02:00
"default": 1.1,
Settings menu modularized. Help text added to settings items. Settings now saved to client file when changed. Separated transformers settings and InferKit settings. Reorganized model select list.
2021-05-07 20:32:10 +02:00
"tooltip": "Used to discard unlikely text in the sampling process. Lower values will make text more predictable but can become repetitious."
},
top_k and tfs support by Frogging101 Adds top_k and tfs support, also fixes a SocketIO error.
2021-08-19 14:47:57 +02:00
{
"uitype": "slider",
"unit": "int",
"label": "Top k Sampling",
"id": "settopk",
"min": 0,
"max": 100,
"step": 1,
"default": 0,
"tooltip": "Alternative sampling method, can be combined with top_p."
},
{
"uitype": "slider",
"unit": "float",
"label": "Tail-free Sampling",
"id": "settfs",
"min": 0.0,
"max": 1.0,
"step": 0.05,
"default": 0.0,
"tooltip": "Alternative sampling method; it is recommended to disable (set to 0) top_p and top_k if using this. 0.95 is thought to be a good value."
},
Settings menu modularized. Help text added to settings items. Settings now saved to client file when changed. Separated transformers settings and InferKit settings. Reorganized model select list.
2021-05-07 20:32:10 +02:00
{
"uitype": "slider",
"unit": "int",
"label": "Amount to Generate",
"id": "setikgen",
"min": 50,
"max": 3000,
"step": 2,
"default": 200,
"tooltip": "Number of characters the AI should generate."
Added option to generate multiple responses per action. Added ability to import World Info files from AI Dungeon. Added slider for setting World Info scan depth. Added toggle to control whether prompt is submitted each action. Added 'Read Only' mode with no AI to startup. Fixed GPU/CPU choice prompt appearing when GPU isn't an option. Added error handling to generator calls for CUDA OOM message Added generator parameter to only return new text
2021-05-29 11:46:03 +02:00
},
{
"uitype": "slider",
"unit": "int",
"label": "W Info Depth",
"id": "setwidepth",
"min": 1,
"max": 5,
"step": 1,
Random Story Generator Add the Random Story Generator and more userfriendly defaults
2021-08-19 12:54:44 +02:00
"default": 3,
Added option to generate multiple responses per action. Added ability to import World Info files from AI Dungeon. Added slider for setting World Info scan depth. Added toggle to control whether prompt is submitted each action. Added 'Read Only' mode with no AI to startup. Fixed GPU/CPU choice prompt appearing when GPU isn't an option. Added error handling to generator calls for CUDA OOM message Added generator parameter to only return new text
2021-05-29 11:46:03 +02:00
"tooltip": "Number of historic actions to scan for W Info keys."
},
Setting Toggles Reordering Bit more alphabetical and a (in my eyes) more logical order of the settings.
2022-01-20 19:23:23 +01:00
{
"uitype": "toggle",
"unit": "bool",
"label": "Auto Save",
"id": "autosave",
"min": 0,
"max": 1,
"step": 1,
"default": 0,
"tooltip": "Whether the game is saved after each action."
},
Added option to generate multiple responses per action. Added ability to import World Info files from AI Dungeon. Added slider for setting World Info scan depth. Added toggle to control whether prompt is submitted each action. Added 'Read Only' mode with no AI to startup. Fixed GPU/CPU choice prompt appearing when GPU isn't an option. Added error handling to generator calls for CUDA OOM message Added generator parameter to only return new text
2021-05-29 11:46:03 +02:00
{
"uitype": "toggle",
"unit": "bool",
"label": "Always Add Prompt",
"id": "setuseprompt",
"min": 0,
"max": 1,
"step": 1,
"default": 1,
"tooltip": "Whether the prompt should be sent in the context of every action."
Integrated VE_FORBRYDERNE's Adventure Mode + Cleanup Adventure Mode allows you to play this like AID, perfect for Choose your own Adventure models
2021-08-19 13:18:01 +02:00
},
{
"uitype": "toggle",
"unit": "bool",
Setting Toggles Reordering Bit more alphabetical and a (in my eyes) more logical order of the settings.
2022-01-20 19:23:23 +01:00
"label": "Adventure Mode",
"id": "setadventure",
Chat Mode The Initial commit for Chat Mode, the nickname part of the UI is missing other than that it should be fully functional. To use Chat Mode effectively you first input a small dialogue (Can be around 6 lines 3 of your own inputs and 3 of the character) formatted as Name : it will then automate the actions needed to chat properly. During this mode single line mode is forced on, and Trim Incomplete Sentences is forced off.
2021-12-26 01:51:32 +01:00
"min": 0,
"max": 1,
"step": 1,
"default": 0,
Setting Toggles Reordering Bit more alphabetical and a (in my eyes) more logical order of the settings.
2022-01-20 19:23:23 +01:00
"tooltip": "Turn this on if you are playing a Choose your Adventure model."
Chat Mode The Initial commit for Chat Mode, the nickname part of the UI is missing other than that it should be fully functional. To use Chat Mode effectively you first input a small dialogue (Can be around 6 lines 3 of your own inputs and 3 of the character) formatted as Name : it will then automate the actions needed to chat properly. During this mode single line mode is forced on, and Trim Incomplete Sentences is forced off.
2021-12-26 01:51:32 +01:00
},
{
"uitype": "toggle",
"unit": "bool",
Setting Toggles Reordering Bit more alphabetical and a (in my eyes) more logical order of the settings.
2022-01-20 19:23:23 +01:00
"label": "Chat Mode",
"id": "setchatmode",
Integrated VE_FORBRYDERNE's Adventure Mode + Cleanup Adventure Mode allows you to play this like AID, perfect for Choose your own Adventure models
2021-08-19 13:18:01 +02:00
"min": 0,
"max": 1,
"step": 1,
"default": 0,
Setting Toggles Reordering Bit more alphabetical and a (in my eyes) more logical order of the settings.
2022-01-20 19:23:23 +01:00
"tooltip": "This mode optimizes KoboldAI for chatting."
Add Memory box to Random Story dialog and "Random Story Persist"
2021-12-30 05:15:59 +01:00
},
{
"uitype": "toggle",
"unit": "bool",
"label": "No Prompt Generation",
"id": "setnopromptgen",
"min": 0,
"max": 1,
"step": 1,
"default": 0,
"tooltip": "When enabled the AI does not generate when you enter the prompt, instead you need to do an action first."
},
{
"uitype": "toggle",
"unit": "bool",
"label": "Random Story Persist",
"id": "setrngpersist",
"min": 0,
"max": 1,
"step": 1,
"default": 0,
"tooltip": "When enabled, the Memory text box in the Random Story dialog will be prefilled by default with your current story's memory instead of being empty."
Fix for redo with options. Added debug menu
2022-01-24 18:54:44 +01:00
},
{
"uitype": "toggle",
"unit": "bool",
"label": "Debug",
"id": "debug",
"min": 0,
"max": 1,
"step": 1,
"default": 0,
"tooltip": "Show debug info"
Setting Toggles Reordering Bit more alphabetical and a (in my eyes) more logical order of the settings.
2022-01-20 19:23:23 +01:00
}
]
Added Formatting options Added Bootstrap toggle library for UI Added injection points for input/output modification
2021-05-11 01:17:10 +02:00
formatcontrols = [{
"label": "Trim incomplete sentences",
"id": "frmttriminc",
"tooltip": "Remove text after last sentence closure. If no closure is found, all tokens will be returned."
},
{
"label": "Remove blank lines",
"id": "frmtrmblln",
"tooltip": "Replace double newlines (\\n\\n) with single newlines to avoid blank lines."
},
{
"label": "Remove special characters",
"id": "frmtrmspch",
"tooltip": "Remove special characters (@,#,%,^, etc)"
},
{
"label": "Add sentence spacing",
"id": "frmtadsnsp",
"tooltip": "If the last action ended with punctuation, add a space to the beginning of the next action."
Single Line Mode Adds Single Line mode, optimized for things like chatbot testing and other cases where you want to have control over what happens after a paragraph. This can also be used as a foundation for a chatbot optimized interface mode.
2021-10-23 17:30:48 +02:00
},
{
"label": "Single Line",
"id": "singleline",
"tooltip": "Only allows the AI to output anything before the enter"
Allow Repetition Penalty up to 3 A user expressed positive feedback when trying higher than 2 repetition penalty on some models, lets allow people the freedom to do so. If there is a demonstrable benefit to running higher than 3 I am open to raising it again.
2021-12-28 03:22:14 +01:00
}]