My SillyTavern settings

#1
by Porcodio - opened

JSON files of my SillyTavern settings:
https://filetransfer.io/data-package/hylxHqJr#link

NeverSleep org

Hello dude, I really appreciate the effort, but can I ask you to upload it on https://catbox.moe/ ?
I can do it if you want, because for whatever reason there is a limit of download on your file.

NeverSleep org

Context : https://files.catbox.moe/vnnsra.json
Instruct : https://files.catbox.moe/7sudj5.json
Preset : https://files.catbox.moe/og94e5.json

Sorry, but I see the download count get down, and I want to save this. Thanks again!

Context : https://files.catbox.moe/vnnsra.json
Instruct : https://files.catbox.moe/7sudj5.json
Preset : https://files.catbox.moe/og94e5.json

Sorry, but I see the download count get down, and I want to save this. Thanks again!

You did the right thing man. Thank you ;)

Sorry but for you this may be very trivial, but for beginners causes questions:

Quote from model card:
"You need to use our custom prompting format(scroll down to see them! or just directly download the SillyTavern instruct preset here)"

Could you please explain where we have to put the json file in Sillytavern? (add it via gui (How?Where? or put it somewhere in the folderstructure of SillyTavern?)

Do we need those files as well? Or are they optional (for experimenting and feedback)?

"
Context : https://files.catbox.moe/vnnsra.json
Instruct : https://files.catbox.moe/7sudj5.json
Preset : https://files.catbox.moe/og94e5.json
"

NeverSleep org

Sorry but for you this may be very trivial, but for beginners causes questions:

Quote from model card:
"You need to use our custom prompting format(scroll down to see them! or just directly download the SillyTavern instruct preset here)"

Could you please explain where we have to put the json file in Sillytavern? (add it via gui (How?Where? or put it somewhere in the folderstructure of SillyTavern?)

Do we need those files as well? Or are they optional (for experimenting and feedback)?

"
Context : https://files.catbox.moe/vnnsra.json
Instruct : https://files.catbox.moe/7sudj5.json
Preset : https://files.catbox.moe/og94e5.json
"

In each of the setting, you have this button:

image.png

Then you can import a json file.
We provided only the Instruct json, that's all you need to run it basically.
The OP provided Advanced Formatting, Instruct, and Preset settings, you can import them too in the same way.

Trying the model out on OpenRouter now that it's on there. What selection for tokenizer? Mistral?

Can someone help? I'm running this model using llama.cpp with the following command

./server -m $MODEL -c 32768

With SillyTavern using the setting json files in this post, but the model keeps endlessly generating, sometimes with some special sequences in the text, such as square brackets [ ] or <im_end> <im_start>

I have never understood how to configure Mixtral with llama.cpp and SillyTavern properly, I've tried 3 Mixtral models with and without the default Mixtral configuration on SillyTavern and the result is the same :(

Hey Porcodio,

We are a small dev. team developing a platform made for those who are serious about crafting amazing prompts and AI roleplaying; it's called [astrsk.ai]!
(check out https://join.astrsk.ai/ for more info.)

We’re looking for 30 passionate users for astrsk.ai's first private beta and would like to invite you to be a part of it!
Please DM me on discord(_cyoo) if you want to participate in the beta and I can give you access.

The selected users will be given early access to the app to test things out, and help us shape the platform into something incredible!
With the private beta you’ll get:

  • Early access to astrsk.ai before anyone else.
  • A chance to customize/play epic AI RP sessions.
  • Direct input on features—we want to hear your ideas.
  • To be part of a tight-knit group of just 30 AI RP and LLM customization enthusiasts who share your passion.

Also, if you know someone else who’d love it, please spread the word!
We want to make sure the beta gets into the hands of people who really care about AI roleplay.
Anyone can apply to our private beta directly through this link(https://forms.gle/mqukoijSg1VXZUFZ9) or via https://join.astrsk.ai/)!

If you are not interested, sorry for spamming your discussion board.
But we would truly love it if you could join the beta.

Thanks!
The astrsk.ai Team

@cyoo soso,the page says you can stay anonymous, and then forces people to sign in via google. that gives a whole new meaning to anonymous.

@mradermacher One of our key features is that all your data stays with you in your local device and no one else has access to it. And we are also actively looking for feedback, so if being anonmyous is important to our users, we are certainly open to adding such features. So if you are interested, please apply to the beta and lets make astrsk.ai together!! :))

I just pointed out that requiring a google login and saying you stay anonymous doesn't go together, even if you might not receive my identity, google does, which might be even worse. I am trying to help you by pointing out that the gut reaction of somebody who is privacy-sensitive (as many hf users are) is to distrust a service that requires a google login while claiming it is anonymous.

Sign up or log in to comment