-
Notifications
You must be signed in to change notification settings - Fork 16
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
6 changed files
with
104 additions
and
25 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,68 @@ | ||
{ | ||
"presetVersion": 3, | ||
"name": "Cosmic Cube", | ||
"id": "7a428c5f-a054-4663-8edd-e24c50cafeea", | ||
"remoteId": "", | ||
"parameters": { | ||
"textGenerationSettingsVersion": 5, | ||
"temperature": 0.9, | ||
"max_length": 40, | ||
"min_length": 1, | ||
"top_k": 0, | ||
"top_p": 1, | ||
"top_a": 0, | ||
"typical_p": 0.924, | ||
"tail_free_sampling": 0.92, | ||
"repetition_penalty": 3, | ||
"repetition_penalty_range": 4000, | ||
"repetition_penalty_slope": 0, | ||
"repetition_penalty_frequency": 0, | ||
"repetition_penalty_presence": 0, | ||
"repetition_penalty_default_whitelist": false, | ||
"cfg_scale": 1.48, | ||
"cfg_uc": "", | ||
"phrase_rep_pen": "off", | ||
"top_g": 0, | ||
"mirostat_tau": 4.95, | ||
"mirostat_lr": 0.22, | ||
"order": [ | ||
{ | ||
"id": "mirostat", | ||
"enabled": true | ||
}, | ||
{ | ||
"id": "cfg", | ||
"enabled": true | ||
}, | ||
{ | ||
"id": "typical_p", | ||
"enabled": true | ||
}, | ||
{ | ||
"id": "temperature", | ||
"enabled": true | ||
}, | ||
{ | ||
"id": "tfs", | ||
"enabled": true | ||
}, | ||
{ | ||
"id": "top_k", | ||
"enabled": false | ||
}, | ||
{ | ||
"id": "top_a", | ||
"enabled": false | ||
}, | ||
{ | ||
"id": "top_g", | ||
"enabled": false | ||
}, | ||
{ | ||
"id": "top_p", | ||
"enabled": false | ||
} | ||
] | ||
}, | ||
"model": "kayra-v1" | ||
} |
2 changes: 1 addition & 1 deletion
2
novelai_api/presets/presets_kayra_v1/Green Active Writer.preset
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
af9ebf2
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Hey everyone @Aedial @bdavs @arthus-leroy @Cikmo
I am working on a game project and wanted to integrate this Novelai api in it,
I can run generatetext.py well but I don't understand how to provide context of previous generations and continue the same story like in NovelAI, everytime I call it's just an individual generation.
I did not knew how to reach out so I am commenting here, Can anyone here please help me with it?
af9ebf2
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Hello @Devansh-kajve,
The context is all one big box where you put what the AI needs to see (the prompt argument). As such, you should append the new text to the old and cut text to fit the context size allowed by your subscription tier (3k for Tablet, 6k for Scroll, 8k for Opus, generation length included). If you do not cut, the AI will cut from the top of context, which might end in the middle of a sentence (so it's important to do it from your side).
Next time you want to ask a question, open an issue, I will get notified of it. No need to ping contributors.
af9ebf2
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thanks for replying, I do have some other questions, asking them in issue