Create and Fuck your AI Cum Slut -70% OFF
x
4.40 star(s) 14 Votes

Gizza

New Member
Mar 14, 2018
14
3
113
Is there a way to turn off the Memory optimization: Trimmed prompt?
Ive noticed this is pretty aggressive and results in the AI only looking at the last 2 or 3 lines of a prompt and ignores everything before it.
 
  • Like
Reactions: Serpream

Deathend

Newbie
Nov 3, 2017
48
21
143
tried to register an account and got this Unexpected token '<', "<!DOCTYPE "... is not valid JSON, im using version 1.1.11 of the downloadable version with a local Ai on LLM.

Also someone has a good way to create a hunger and a stamina sistems?

and another thing, has anyone found out why sometimes traits dont work? i have two worlds created by me, on the older one traits get added correctly at the start of the world and in the new wan, the chosen traits dont get added to the player at the start of the game.
 
Last edited:

draxton

Newbie
Dec 10, 2019
53
86
226
tried to register an account and got this Unexpected token '<', "<!DOCTYPE "... is not valid JSON, im using version 1.1.11 of the downloadable version with a local Ai on LLM.
Likely server crashed and is throwing an error page (HTML) instead of returning a proper JSON response

Confirmed, server issue:
502 Bad Gateway
Unable to reach the origin service. The service may be down or it may not be responding to traffic from ***************
 
Last edited:

fierylion

Member
Game Developer
Jan 18, 2019
314
508
228
Likely server crashed and is throwing an error page (HTML) instead of returning a proper JSON response

Confirmed, server issue:
502 Bad Gateway
Unable to reach the origin service. The service may be down or it may not be responding to traffic from ***************
there was a power outage ya
 

Deathend

Newbie
Nov 3, 2017
48
21
143
yes it seems it was the servers, managed to do the acount, and for some reason the traits in the new world now work fine.
now im trying to make the stat systems, specificaly a hunger/health sistem where health regeneration is based on hunger stat (0 feed, 100 starving) but the code i tried gives error so no idea if im even close XD, also want to add a stamina system that works with how intense interactions are but havent started with it nor i now where to start.
 

Deathend

Newbie
Nov 3, 2017
48
21
143
Found a bug if editing the world in the middle of the game, traits that change stats values get also aded to the world edit causing it to acumulate with each new game and edit.
i created the fertility trait that increases starting fertility by 100 and the base starting value for fertility is also 100 (so 200 if starting with the trait) but if i chose the trait and click edit wotld the vase fertility value in the stat gets changed to the new value.
resume:

base stat in world edit is 100, open world and chose trait hitting confirm, hit world edit button in game, base stat is now 200 in the world edit.

Also i have a sugestion for the trait system, Conflicting traits, on the traits themselves other traits are shown (like entities are shown on locations) and chosing a trait on game start blocks the player from chosing any trait marked as conflicting for that trait.

Taking advantage that my post is still the last post i will post another sugestion in this post XD

Stats that depend on traits, for example im creating a Lactation trait, but i would like to create a stat for milk amount that only shows if the player has the trait otherwise is should be a stat that dont appear on the list and the Ai ignores.
 
Last edited:

Mellech

Newbie
Aug 30, 2017
21
13
197
Here's my template that I use to make new worlds easier. I use mistral nemo 2407 and it seems to follow instructions quite well. Just copy-paste into system prompt and add your info under each section. Create entities based on your "**Side characters**" section for the AI to remember the info properly.
I usually don't dabble in traits or dictionary so any suggestions are more than welcome.
 

derp752

Member
Apr 22, 2019
143
188
208
I have this bug thats recently started happening. It keeps repeating this over and over at some point after maybe 10 passages
You don't have permission to view the spoiler content. Log in or register now.
 

mimospros

Member
Apr 2, 2018
196
99
145
Does size have to do with anything? That one is 40GB, I tried running , but every iteration took a lot of time and lagged my computer and it's only 12GB.

runs smoothly, and it's 7GB. Is that the size in disk or the size it'll occupy in the vram?
what's you PC specs?
And yeah, of course size matters. Just... Look at thos 8B-12B-22B in model names or on download sources in 'model size' part. For example - my PC have 8GB vram and 16GB ram and capable to partially smoothly run 8B (not a GB, but B, like, 8 billion parameters), and with a little more effort - 12B GGUF model, at 14B model it starts to genery too slow to be enjoyable and larger models makes my PC to really struggle while generating like 1 symbol per 5-10 seconds, which is VERY slow. GGUF models capable to run not only on your VRAM memory but also offloads some exceed usage onto your processor, so be careful not ot cook your PC when you try to run bigger models. If your PC is capable to smoothly run 12B model (mistral nemo instruct from your link IS 12B model) than if you really want some real horny advetures I can recommend model. ALSO pay attention to model names. If they contain 'instruct' then those models were trained to follow exact instructions given, which often follows with... boring for a roleplay. RP in name of model means that this model is better suited for roleplays. Beside RP and INSTRUCT there also some more key words in model names (like abliterated or distilled, never download these ones - really poor quality for roleplays).
Aside from number of parameters, GGUF models have an QUANTISATIONS - q_3, q_4, q-5, q_5_s, q_5_m e.t.c. I, myself, prefer to run 12B with Q_5_M (or higher if model is smaller) since with lower quants models loose more data and have less quality.
Oh, and never forget, that contex length also eats resources, so try not to max it when you launch model, better set it to more... suited for your PC numbers of tokens.
AND YES, when you run model it fully loads onto your VRAM!!! So if your PC is not equipped with 40GB VRAM videocard or sum of your VRAM + RAM isn't more than 40GB then better do not try to run such big models.
 
Last edited:
  • Like
Reactions: Mellech and ich0

mimospros

Member
Apr 2, 2018
196
99
145
I have this bug thats recently started happening. It keeps repeating this over and over at some point after maybe 10 passages
That's happens with AI. I guess (only guess!!!), that this happens when context memory fills and old messages getting cut at some point from memory, with your case AI got context that started with or ended with <special_38> without pointers where is whose message and as result AI recognised that it was continuosly repeating this special _38 as it's own messages and decided just to continue doing what it was doing. OR you simply had TEMP value too low for your running model :LOL:
 

Breedking

Newbie
Jul 7, 2024
69
39
95
model.
Are there versions of the Angel Slayer that aren't max RPG? Having the AI decide player actions is pretty annoying, but I really liked the detail and how fast the response time was. Everything I searched was only showing the RPGMax versions though.
 

Mellech

Newbie
Aug 30, 2017
21
13
197
what's you PC specs?
And yeah, of course size matters. Just... Look at thos 8B-12B-22B in model names or on download sources in 'model size' part. For example - my PC have 8GB vram and 16GB ram and capable to partially smoothly run 8B (not a GB, but B, like, 8 billion parameters), and with a little more effort - 12B GGUF model, at 14B model it starts to genery too slow to be enjoyable and larger models makes my PC to really struggle while generating like 1 symbol per 5-10 seconds, which is VERY slow. GGUF models capable to run not only on your VRAM memory but also offloads some exceed usage onto your processor, so be careful not ot cook your PC when you try to run bigger models. If your PC is capable to smoothly run 12B model (mistral nemo instruct from your link IS 12B model) than if you really want some real horny advetures I can recommend model. ALSO pay attention to model names. If they contain 'instruct' then those models were trained to follow exact instructions given, which often follows with... boring for a roleplay. RP in name of model means that this model is better suited for roleplays. Beside RP and INSTRUCT there also some more key words in model names (like abliterated or distilled, never download these ones - really poor quality for roleplays).
Aside from number of parameters, GGUF models have an QUANTISATIONS - q_3, q_4, q-5, q_5_s, q_5_m e.t.c. I, myself, prefer to run 12B with Q_5_M (or higher if model is smaller) since with lower quants models loose more data and have less quality.
Oh, and never forget, that contex length also eats resources, so try not to max it when you launch model, better set it to more... suited for your PC numbers of tokens.
AND YES, when you run model it fully loads onto your VRAM!!! So if your PC is not equipped with 40GB VRAM videocard or sum of your VRAM + RAM isn't more than 40GB then better do not try to run such big models.
For some reason AngelSlayer has tremendous issues when generating choices, sometimes continuously generating text in the choice boxes and after generating a huge wall of text, the choices reduce to just 6 boxes that make little sense given the instructions. Other times it generates all sorts of extra weird words like |lim_"something something or other"|

Edit: kept testing it for a bit and noticed it is very inconsistent with its generating speeds and "<|im_end|><|im_end|><|im_end|>" keeps appearing in the game text and choices.
Edit 2: Yeah, no. It keeps either taking a while to generate 2-3 paragraphs or instantly starts rolling out a huge wall of text with <|im_end|><|im_start|>user or <|im_start|>assistant sprinkled in and continues being very inconsistent in its generation. It's a shame since the text itself looks fine at first glance. I'm guessing that this model requires certain commands to be set in its own parameter language.
Tested with 1.11.1 and it kinda sorta maybe worked 25% of the time, but 1.20 was a flustercuck.
Honestly, I've found that only mistral nemo 2407 doesn't go completely ballistic with generation.
 
Last edited:

mimospros

Member
Apr 2, 2018
196
99
145
For some reason AngelSlayer has tremendous issues when generating choices, sometimes continuously generating text in the choice boxes and after generating a huge wall of text, the choices reduce to just 6 boxes that make little sense given the instructions. Other times it generates all sorts of extra weird words like |lim_"something something or other"|

Edit: kept testing it for a bit and noticed it is very inconsistent with its generating speeds and "<|im_end|><|im_end|><|im_end|>" keeps appearing in the game text and choices.
Edit 2: Yeah, no. It keeps either taking a while to generate 2-3 paragraphs or instantly starts rolling out a huge wall of text with <|im_end|><|im_start|>user or <|im_start|>assistant sprinkled in and continues being very inconsistent in its generation. It's a shame since the text itself looks fine at first glance. I'm guessing that this model requires certain commands to be set in its own parameter language.
Tested with 1.11.1 and it kinda sorta maybe worked 25% of the time, but 1.20 was a flustercuck.
Honestly, I've found that only mistral nemo 2407 doesn't go completely ballistic with generation.
Using in silly tavern I never had such issue with angel slayer. But I can guess what is going on! Different models need different settings! And I'm talking not only about those shady TOP-K TOP-P, nor it's about even TEMP settings! Those "<|im_end|><|im_start|>" telling us what is issue! In Silly Tavern you can change context templates and for different releases of models, if turned on, it automatically changes to needed. In this game we don't have this function. Here how it should look:
<|im_start|>system
{{#if system}}{{system}}
{{/if}}{{#if wiBefore}}{{wiBefore}}
{{/if}}{{#if description}}{{description}}
{{/if}}{{#if personality}}{{char}}'s personality: {{personality}}
{{/if}}{{#if scenario}}Scenario: {{scenario}}
{{/if}}{{#if wiAfter}}{{wiAfter}}
{{/if}}{{#if persona}}{{persona}}
{{/if}}{{trim}}<|im_end|>

For Mistral it sligtly differs:
[SYSTEM_PROMPT] {{#if system}}{{system}}
{{/if}}{{#if wiBefore}}{{wiBefore}}
{{/if}}{{#if description}}{{description}}
{{/if}}{{#if personality}}{{personality}}
{{/if}}{{#if scenario}}{{scenario}}
{{/if}}{{#if wiAfter}}{{wiAfter}}
{{/if}}{{#if persona}}{{persona}}
{{/if}}{{trim}}[/SYSTEM_PROMPT]

And all models with equal number of parameters generate response with same pace, sometimes a LITTLE slower or faster. It's just, for example, if AI uses those macroses, like when it uses start of paragraph with name of {{char}} - the name generates at first until it fully finshed, then it dissapears! It's not model issue - it's like using some symbols, that you need to type few different letters before whatever Word Pad you use will recognise it and replace it with corresponding symbol - slowdown simply visual, if you look at console of running AI you will see that tokens generate at same pace.

As summary I can say: the fact that you see those symbols is simply because game, it seems, isn't set to play with CHAT_ML template. That disappointing. Because instruct models IS lacking in a diversity of possible responses due slope tokens (tokens, that AI tend to use more often, than other tokens). Instruct models is built to complete tasks as precisely as possible for them. I really like AngelSlayer model (if more correctly - I like the combination of models used, it gave very good expierence model and it responds like if actually manages to analyse situation, instead of simply... continuing already exsisting text.

EDIT: Potetially the solution is also write down your own template for this task, since we want AI to track stats and give options to choose aside from just playing role of {{char}}.
 
Last edited:

Mellech

Newbie
Aug 30, 2017
21
13
197
Using in silly tavern I never had such issue with angel slayer. But I can guess what is going on! Different models need different settings! And I'm talking not only about those shady TOP-K TOP-P, nor it's about even TEMP settings! Those "<|im_end|><|im_start|>" telling us what is issue! In Silly Tavern you can change context templates and for different releases of models, if turned on, it automatically changes to needed. In this game we don't have this function. Here how it should look:
<|im_start|>system
{{#if system}}{{system}}
{{/if}}{{#if wiBefore}}{{wiBefore}}
{{/if}}{{#if description}}{{description}}
{{/if}}{{#if personality}}{{char}}'s personality: {{personality}}
{{/if}}{{#if scenario}}Scenario: {{scenario}}
{{/if}}{{#if wiAfter}}{{wiAfter}}
{{/if}}{{#if persona}}{{persona}}
{{/if}}{{trim}}<|im_end|>

For Mistral it sligtly differs:
[SYSTEM_PROMPT] {{#if system}}{{system}}
{{/if}}{{#if wiBefore}}{{wiBefore}}
{{/if}}{{#if description}}{{description}}
{{/if}}{{#if personality}}{{personality}}
{{/if}}{{#if scenario}}{{scenario}}
{{/if}}{{#if wiAfter}}{{wiAfter}}
{{/if}}{{#if persona}}{{persona}}
{{/if}}{{trim}}[/SYSTEM_PROMPT]

And all models with equal number of parameters generate response with same pace, sometimes a LITTLE slower or faster. It's just, for example, if AI uses those macroses, like when it uses start of paragraph with name of {{char}} - the name generates at first until it fully finshed, then it dissapears! It's not model issue - it's like using some symbols, that you need to type few different letters before whatever Word Pad you use will recognise it and replace it with corresponding symbol - slowdown simply visual, if you look at console of running AI you will see that tokens generate at same pace.

As summary I can say: the fact that you see those symbols is simply because game, it seems, isn't set to play with CHAT_ML template. That disappointing. Because instruct models IS lacking in a diversity of possible responses due slope tokens (tokens, that AI tend to use more often, than other tokens). Instruct models is built to complete tasks as precisely as possible for them. I really like AngelSlayer model (if more correctly - I like the combination of models used, it gave very good expierence model and it responds like if actually manages to analyse situation, instead of simply... continuing already exsisting text.
Thanks for the explanation. I should probably try using SillyTavern as well and see how that pans out.
 

Deathend

Newbie
Nov 3, 2017
48
21
143
can someone give me a hand with dynamic stat code? i have a fertility stat that is supposes to be the base fertility value plus 25% of health, it is settled well at the start of the game but after every prompt the calculation increases again topping the stat in two prompts even tough helalt is going down instead of up.

You don't have permission to view the spoiler content. Log in or register now.

i have no idea if the problem is in the code, the ai or the game doing something weird.
 

Hollex

Newbie
Jan 10, 2025
52
69
28
can someone give me a hand with dynamic stat code? i have a fertility stat that is supposes to be the base fertility value plus 25% of health, it is settled well at the start of the game but after every prompt the calculation increases again topping the stat in two prompts even tough helalt is going down instead of up.

You don't have permission to view the spoiler content. Log in or register now.

i have no idea if the problem is in the code, the ai or the game doing something weird.
This has to do with how you've entered the code.

Let's look at an example.

You don't have permission to view the spoiler content. Log in or register now.

As you can see when doing the calculations, fertility initially increases due to health, but as fertility increases, it causes fertility to increase again in the next round of calculations, repeating in a cycle until fertility is maximized.

I propose the following solutions to you:

You don't have permission to view the spoiler content. Log in or register now.
Or
You don't have permission to view the spoiler content. Log in or register now.
I sincerely believe that what you are looking for is the second option and for this you do not have to take the current fertility value but the base fertility value that you define yourself.
 
  • Like
Reactions: Deathend

Deathend

Newbie
Nov 3, 2017
48
21
143
This has to do with how you've entered the code.

Let's look at an example.

You don't have permission to view the spoiler content. Log in or register now.

As you can see when doing the calculations, fertility initially increases due to health, but as fertility increases, it causes fertility to increase again in the next round of calculations, repeating in a cycle until fertility is maximized.

I propose the following solutions to you:

You don't have permission to view the spoiler content. Log in or register now.
Or
You don't have permission to view the spoiler content. Log in or register now.
I sincerely believe that what you are looking for is the second option and for this you do not have to take the current fertility value but the base fertility value that you define yourself.

thanks, would the second option work with a trait that changes fertility, one of the posible traits i made is fertile witch doubles the initial base value of the stat.

no, it does not work with traits, i suspect that it can be included with an if/else code, but i have no idea how to code that, i can somewhat read code but i have no idea of how to write it.

i have added this to the code
You don't have permission to view the spoiler content. Log in or register now.
but as i said i have no idea how to write it, i suspect the trait part is wrongly written but have no idea
 
Last edited:

Hollex

Newbie
Jan 10, 2025
52
69
28
thanks, would the second option work with a trait that changes fertility, one of the posible traits i made is fertile witch doubles the initial base value of the stat.

no, it does not work with traits, i suspect that it can be included with an if/else code, but i have no idea how to code that, i can somewhat read code but i have no idea of how to write it.

i have added this to the code
You don't have permission to view the spoiler content. Log in or register now.
but as i said i have no idea how to write it, i suspect the trait part is wrongly written but have no idea
I honestly don't know if traits are supported but it definitely has to be something like this.
You don't have permission to view the spoiler content. Log in or register now.

Honestly, it's possible that we don't even have access to the traits in the dynamic code, and if we do, I have no idea how the trait object's properties are structured.

Probably the only one who can tell you for sure is fierylion.
 

Deathend

Newbie
Nov 3, 2017
48
21
143
I honestly don't know if traits are supported but it definitely has to be something like this.
You don't have permission to view the spoiler content. Log in or register now.

Honestly, it's possible that we don't even have access to the traits in the dynamic code, and if we do, I have no idea how the trait object's properties are structured.

Probably the only one who can tell you for sure is fierylion.
nop, when adding that to the code it breaks and goes to the default setting, so or there is no way to link dynamic code to traits yet or somewhere in that part of the code is missing something so ill wait for fierylion to comfirm if traits can be linked

now, on other code problem im having, how does one include a negative value to the code? im trying to make health regenerate or loss depending on a Nutrition trait, but the code i have half works and it seems to break the starting healt value when the game starts.

You don't have permission to view the spoiler content. Log in or register now.

when i use this code the game actually regenerathes 2 health per turn if nutrition is avobe 50, but at the start of the game health goes imediately to 0 and then it aplies the regeneration, so no mather how much healt is assigned at the game start you end with 2 on game start.

Note: i wanted to make the healt regen a total of 4 values basing them on the nutrition stages ive set, but i had 0 idea on how to do that so i comformed y 2 values only.
 
Last edited:
4.40 star(s) 14 Votes