TavernAI Character List

[blyatman]

is their any easy way to just download it?

Click the link, follow the instructions. There's a downloadable exe file there.

im reffering to the google part i have to have that running to work right? is there any way i can just download it whithout dealing with all the complexity

[tonyvld]

Seems like things are down right now? Like, I got it running like before, but now it's just refusing to connect? Anyone else getting this issue right now?

[MasterMage13]

is their any easy way to just download it?

Click the link, follow the instructions. There's a downloadable exe file there.

im reffering to the google part i have to have that running to work right? is there any way i can just download it whithout dealing with all the complexity

Yes you have to run the model in Google Colab.

If you know what you're doing you probably could download and run the model locally but you would need a pretty powerful computer to do that. It would be a lot more complex, actually. If you really really want to, you can find it here: https://github.com/koboldai/koboldai-client and go down to the "Install KoboldAI on your own computer" section. You'll still need to install Tavern AI. Tavern AI is the front-end.

Basically what you are doing is, you are running the AI model in Google Colab, the model once it is started will give you a URL. That URL links to the container that the model is running from. Then you run Tavern.AI on your local machine, which creates a local web server. So it's like a website running on your PC. Then you paste that URL you got from the Google Colab notebook. That links your instance of Tavern.AI to the model you are running in Google Colab.

how can i copy the api url from the list? it is my first time using this kind of program

After you start the model in the Colab notebook just wait, you're going to see a whole bunch of stuff happening. That's the script installing the model in your Google Colab instance. It takes a few minutes. Just wait until it is done doing everything.

When it's all done:

In black it says "Setting Seed" <-- you need to wait until you see this. This means it's ready.

Below that in green:
KoboldAI has finished loading and is available at the following link for UI 1: (And a URL)
KoboldAI has finished loading and is available at the following link for UI 2: (And a URL)

UI 1 is the one you want to copy into API url. That's the link to your instance of the model. It will be different every time. And yes you need to keep the browser with the Colab notebook open the whole time you are using it.

Ok, so I launched tavern.AI.exe, it opened up the main webpage I went to chat with a character but on the bottom it says "No Connection" and won't let me talk. Anyone got some tips and pointers for me on that?

In that web page: Go to "Settings". Go down to "API url". Paste the URL mentioned above into there. Click "Connect". Don't forget to click on Master Settings while you're in there and turn down the Context Size to ~1400.

Not sure bout the tokens part of it, I just run it and let it do what it needs to.

You need to lower the Context Size tokens because if you try to keep 2048 tokens in memory you will go over the free GPU memory limit on your Google Colab instance. There's a finite amount of memory available and if you use it all up the model will crash. If you use too many tokens the model might run out of memory before returning anything.

Seems like things are down right now? Like, I got it running like before, but now it's just refusing to connect? Anyone else getting this issue right now?

Google Colab might kick you off after a while and you will need to restart the model.

Is there any restrictions to this AI? Like can you get banned for NSFW or vore actions? or is this an offline/standalone client?

No. It's your own private little instance of the model. Or, at least, it's as private as any other thing running from a free Google service. And KoboldAI doesn't care. They have multiple models trained on NSFW content. Though... as far as vore goes... its' about as good at it as any other GPT-6b knock off is. Which is to say it doesn't really "get" it. So you kinda have to coax it.

And all your stuff is stored locally. Your chats and whatever characters you load from the presets or that you import. Look in the TavernAI-main\public\ folder. Characters has the character avatar images and Chats has the .json files which are the chat histories. It's saved locally so you can continue talking to the character if\when you need to restart the model.

[Voremugen]

Sadly its too much of a pain to install. I am a lazy snack. Waiting for a complete-installer or a browser version.

[grandplex]

It isn't just about easiness to install either, until the higher end models (above 6B or 7B) can be run on at least collab, and preferably a consumer pc, it is really doubtful they will be able to run vore properly (but it is still great for other NSFW at that size).

Specifically, yes, at that 6-7B, the models can do it, and you may not even need that much forcing right away, but it will be really short and then start having problems. If you try to do size-play (macro/micro) or something even more rare, it will start getting the responses completely wrong within just one or two messages. The reason CAI was able to do vore well (before the filter), is it is a high parameter model (something like a 30B or a 150B), it has the training size to include vore even during the early days of public release of generative AIs that aren't all that efficient with computer resources.

[Graphis]

Sadly its too much of a pain to install. I am a lazy snack. Waiting for a complete-installer or a browser version.

I feel you, I do. This stuff is good, way better than c.ai, and honestly less work than trying to get stuff going on the chatrooms these days. Though in that case, I am picky. From one lazy bastard to another, I think its worth it.


Though I am suddenly having some problems with it tonight. I'm not getting responses after reloading colab. Does Google cut a user off after so much usage for a time?

[bonberjean]

Sadly its too much of a pain to install. I am a lazy snack. Waiting for a complete-installer or a browser version.

Well... I got good news for you, someone made a mod to make Tavern AI to use KoboldAI Horde
Basically, just follow a few steps and you're done. no need to setup colab or locally... but it takes a while for the responses to be generated

[Graphis]

Though I am suddenly having some problems with it tonight. I'm not getting responses after reloading colab. Does Google cut a user off after so much usage for a time?

Probably not me, I am guessing that people are finding out about it and it's getting tons of traffic. Uh. It really sucks, guys. Stay away.

[Navien]

it cuts you off after a while. its recommended to have miultiple accounts to do all the rping you want

also when your done click manage sessions and end all of them, the thing still runs even if you close the tab

[Graphis]

I have created a pig girl mini giantess with a fondness of boys, Hannah.

https://file.io/gQU9mPq7Lqdz

Back to what the thread was meant for!

[DragOnDude]

I have created a pig girl mini giantess with a fondness of boys, Hannah.

https://file.io/gQU9mPq7Lqdz

Back to what the thread was meant for!

Thank you! Lol, I should 've created 2 separate forum rooms lol. I created a discord where we post characters as well. It's great because it reads the jsons for you before you decide to download it.

[Graphis]

Thank you! Lol, I should 've created 2 separate forum rooms lol. I created a discord where we post characters as well. It's great because it reads the jsons for you before you decide to download it.

All good. The tech support is kinda needed, there's a lot of sporadic documentation out there. I'll probably get on your discord later.

[Molbo]

https://booru.plus/+pygmalion

https://www.characterhub.org

[LLehimera]

I say right away that English is not my native language, and I use a translator.

As far as I know, there should be no censorship on this site, since there are a lot of 18+ chats here. But when it comes to the climax, the bot stops generating text. (I had it with Vore as well)

This problem occurs only in the hottest moment. Is there any way to fix this, or is there nothing that can be done?

[Graphis]

. Is there any way to fix this, or is there nothing that can be done?

I have learned more about this. You are only allowed to use so much of Google Colab for free at a time. There are 3 solutions I know of.

1. Pay Google to use Colab more. They have several options.

2. Wait a few hours, come back to the scene later after your time has reset. I do not know the details of the colab timer.

3. Have multiple accounts, switching to another account when the bot won't respond anymore. You will have to remake the bot for each of your accounts and remind the bot where you are in the scene when you pick it up with another account.

[Navien]

. Is there any way to fix this, or is there nothing that can be done?

I have learned more about this. You are only allowed to use so much of Google Colab for free at a time. There are 3 solutions I know of.

1. Pay Google to use Colab more. They have several options.

2. Wait a few hours, come back to the scene later after your time has reset. I do not know the details of the colab timer.

3. Have multiple accounts, switching to another account when the bot won't respond anymore. You will have to remake the bot for each of your accounts and remind the bot where you are in the scene when you pick it up with another account.

there is one thing you can do to not have to juggle your conversations between accounts. You can download TavernAi in order to have both bots and conversations locally
https://github.com/TavernAI/TavernAI

Then you can use google collab to run koboldAI to putin the API url in order to run the model so you can run Tavern while having Kobold AI running on the cloud. thisway when you swtich accounts it doesn't
https://colab.research.google.com/githu ... /GPU.ipynb

Course if you're on mobile, or dont wanna download tavern ai, you can run both on cloud, but then the bots and conversations would be saved sepreately between accounts, so that'd be complicated, my advice would be just to have conversations with sepreate characters a per account just to make thigns simple. or dont, up to you
https://colab.research.google.com/githu ... /GPU.ipynb