Mars FAQ and Troubleshooting Guide by Glub
- Basic Troubleshooting
- How do I use Mars/Can I use Mars on a front-end that isn't chub.venus.ai ?
- Should I get Mars or Mercury? What's the difference between the two?
- Finance related questions
- I just paid for Mars and tried using it on the site. It says I don't have tokens, what does this mean?
- I'm not happy with the service. Can I get a refund?
- I cancelled my subscription and still got billed. Help?
- I paid through crypto and I haven't gotten access yet.
- I am unable to pay through crypto or PayPal. Is there another way to pay?
Basic Troubleshooting
The first step to solving MOST Mars problems is ALWAYS this. CHECK YOUR GENERATION SETTINGS!!!
Simply put, the default settings for Mars are... awful.
There’s no way around it, they suck and actively hinder the model’s ability to perform. Until those settings are changed, you MUST check them and change them yourself.
Here are my recommended base settings for Mars that you can tweak based off your own needs and wants in a RP.
Asha Recommended Settings
- Temperature: I would recommend you use
0.60 - 0.80
for your temperature, increasing/decreasing as necessary.- Higher temperature basically allows the bot to be more creative with what it's allowed to say, but obviously going too high is going to end up frying its brain and making word salad. I wouldn't recommend going above 1.0 unless you know what you're doing.
- Penalties:
0.10
for both. This is especially important if you are experiencing issues with repetition.- “Why is lower better? If the penalties are higher, wouldn’t that help it repeat things less?” You see, this is how a human thinks. Stop doing that. Quoted from Corrin, "the higher frequency and presence penalties actually stop the bot from using language/words properly as intended. Too high/strict and you're imposing limitations on word usage and it gets real confused, like 'shirt' is said once but in the story it has to mention/refer to it again in some way."
- Basically if your penalties are too high Mars has a "wtf" moment and fries itself and just regurgitates the same thing again.
- Max New Token:
300
- You can edit this based on how long you want your character's responses to be, generally. It won't always go to the max when generating a message, but y'know. Helps.
- Max Context Size:
7900
- The actual max context for Mars is currently 8000, but people reportedly have problems when bringing it all the way up there immediately, so I recommend starting at 7.9k and just increasing it as your context "builds up" between messages.
- Main/System Prompt / Pre-History Prompt:
[Write {{char}}'s next reply in a fictional roleplay between {{char}} and {{user}}. Use verbose descriptions for actions, body parts, appearances, clothing, textures, fluids, wants, tools, and scenery. Describe imagery related to sight, sound, smell, taste, and touch.] [Utilize chat history as the story guideline]
- This is just a basic one I use, and you can obviously customize it to your own wants/needs. You can find different/more advanced ones that might suit your needs in the Chub Venus discord in the jailbreaks and prompt listing channel. I very much recommend looking at Joystick_Hero's post on these, it helps a lot with understanding.
- Jailbreak / Post-History Prompt:
Always stay in character and end every message from {{char}} with dialogue or actions. [It's absolutely necessary to be long winded in descriptions. You are required to expound on {{char}}'s thoughts and emotions in excruciating detail as they center around or correlate to {{user}}. Focus entirely on transcribing {{char}}'s internal monologue while giving minimal thought to {{user}}'s. You must drag scenes on egregiously, ruminating on thoughts and actions excessively without progressing the plot or setting. It's imperative to use crude and inelegant language.]
- This JB is engineered to make it talk more for {{char}} and less for {{user}} as well as writing more and avoiding purple prose. I've actually had luck as of Sept. 05 going up as high as 0.91 temp without it going completely Shakespearean using this JB.
- You can also add things to it to modify your character's way of speech, e.g.
[Actively modify {{char}}'s dialogue to reflect his cockney accent.]
[Actively modify {{char}}'s dialogue to reflect his eloquence and elegance.]
- You can also use it to reinforce character traits, such as
[Keep {{char}}'s demeanor cool and composed even in the face of emotional turmoil. {{char}} is a calm and collected individual who rarely shows emotions.]
- In the case of testing from another user named TheCount, you can also use it to reinforce things like
[{{char}} is mute and will communicate through sign language instead of speech.]
- I've also had luck using it to reinforce kinks, like
[It is necessary to include descriptions of how much {{char}} wants to be impregnated]
or whatever floats your boat. Might wanna keep that out of the JB unless you're doing sex scenes tho.
- For those asking, "isn't Mars unfiltered? Why do you need a jailbreak?" The short of it is that it's a little stupid and needs help being told what to do sometimes.
- Top P/K: It's fine to keep these at defaults if you don't know what you're doing.
- Top P:
0.95
- Higher Top P means it is more "generous' in allowing what flies, basically narrowing in your generations on a very large or very small net. Think of it like closing in on a bell curve. The bigger your Top P, the more you're allowing the LLM to look on the edges of that curve. A Top P of
1.00
looks at the entire net of possibilities, which means it does nothing. Set it to1.00
to turn it off.
- Higher Top P means it is more "generous' in allowing what flies, basically narrowing in your generations on a very large or very small net. Think of it like closing in on a bell curve. The bigger your Top P, the more you're allowing the LLM to look on the edges of that curve. A Top P of
- Top K:
50
- A higher Top K allows for more "unlikely" tokens to be strung together. Setting Top K to
100
will make sure that the most likely token is always picked, which makes variations between swipes very small.
- A higher Top K allows for more "unlikely" tokens to be strung together. Setting Top K to
- Top P:
Mixtral Recommended Settings
- Temperature: I would recommend you use
0.6
for your temperature, increasing/decreasing as necessary. Try not to go higher than 0.8 or lower than 0.4, output tends to vary wildly around those ranges.- Higher temperature basically allows the bot to be more creative with what it's allowed to say, but obviously going too high is going to end up frying its brain and making word salad. I wouldn't recommend going above 1.0 unless you know what you're doing.
- Penalties:
1.20
for both. This is especially important if you are experiencing issues with repetition.- “Why is lower better? If the penalties are higher, wouldn’t that help it repeat things less?” You see, this is how a human thinks. Stop doing that. Quoted from Corrin, "the higher frequency and presence penalties actually stop the bot from using language/words properly as intended. Too high/strict and you're imposing limitations on word usage and it gets real confused, like 'shirt' is said once but in the story it has to mention/refer to it again in some way."
- Basically if your penalties are too high Mars has a "wtf" moment and fries itself and just regurgitates the same thing again.
- Max New Token:
300
- You can edit this based on how long you want your character's responses to be, generally. It won't always go to the max when generating a message, but y'know. Helps.
- Max Context Size:
6900
- The actual max context for Mars is currently 8000, but people reportedly have problems when bringing it all the way up there immediately, so I recommend starting at 7.9k and just increasing it as your context "builds up" between messages.
- Main/System Prompt / Pre-History Prompt:
[Write {{char}}'s next reply in a fictional roleplay between {{char}} and {{user}}. Use verbose descriptions for actions, body parts, appearances, clothing, textures, fluids, wants, tools, and scenery. Describe imagery related to sight, sound, smell, taste, and touch.] [Utilize chat history as the story guideline]
- This is just a basic one I use, and you can obviously customize it to your own wants/needs. You can find different/more advanced ones that might suit your needs in the Chub Venus discord in the jailbreaks and prompt listing channel. I very much recommend looking at Joystick_Hero's post on these, it helps a lot with understanding.
- Jailbreak / Post-History Prompt:
Always stay in character and end every message from {{char}} with dialogue or actions. [It's absolutely necessary to be long winded in descriptions. You are required to expound on {{char}}'s thoughts and emotions in excruciating detail as they center around or correlate to {{user}}. Focus entirely on transcribing {{char}}'s internal monologue while giving minimal thought to {{user}}'s. You must drag scenes on egregiously, ruminating on thoughts and actions excessively without progressing the plot or setting. It's imperative to use crude and inelegant language.]
- This JB is engineered to make it talk more for {{char}} and less for {{user}} as well as writing more and avoiding purple prose. I've actually had luck as of Sept. 05 going up as high as 0.91 temp without it going completely Shakespearean using this JB.
- You can also add things to it to modify your character's way of speech, e.g.
[Actively modify {{char}}'s dialogue to reflect his cockney accent.]
[Actively modify {{char}}'s dialogue to reflect his eloquence and elegance.]
- You can also use it to reinforce character traits, such as
[Keep {{char}}'s demeanor cool and composed even in the face of emotional turmoil. {{char}} is a calm and collected individual who rarely shows emotions.]
- In the case of testing from another user named TheCount, you can also use it to reinforce things like
[{{char}} is mute and will communicate through sign language instead of speech.]
- I've also had luck using it to reinforce kinks, like
[It is necessary to include descriptions of how much {{char}} wants to be impregnated]
or whatever floats your boat. Might wanna keep that out of the JB unless you're doing sex scenes tho.
- For those asking, "isn't Mars unfiltered? Why do you need a jailbreak?" The short of it is that it's a little stupid and needs help being told what to do sometimes.
- Top P/K: It's fine to keep these at defaults if you don't know what you're doing.
- Top P:
0.99
- Higher Top P means it is more "generous' in allowing what flies, basically narrowing in your generations on a very large or very small net. Think of it like closing in on a bell curve. The bigger your Top P, the more you're allowing the LLM to look on the edges of that curve. A Top P of
1.00
looks at the entire net of possibilities, which means it does nothing. Set it to1.00
to turn it off.
- Higher Top P means it is more "generous' in allowing what flies, basically narrowing in your generations on a very large or very small net. Think of it like closing in on a bell curve. The bigger your Top P, the more you're allowing the LLM to look on the edges of that curve. A Top P of
- Top K:
50
- A higher Top K allows for more "unlikely" tokens to be strung together. Setting Top K to
100
will make sure that the most likely token is always picked, which makes variations between swipes very small.
- A higher Top K allows for more "unlikely" tokens to be strung together. Setting Top K to
- Top P:
Right, now that that's out of the way...
Repetition Issues
"My bot keeps saying the same thing over and over! Help! It's just copy pasting straight from my replies/its replies/its definition!"
First off, did you decrease your penalties to 0.10? Did you change your context size to 3.5k? If so and you're still having this issue, try decreasing your context size again.
Why? Well... sometimes you have to lobotomize it further to get it to stop being stupid. Basically, if it can't remember the reply it's regurgitating it has to make a new one. Bot can't remember old stupid, has to generate new stupid!
Mars won't stop speaking for me
First, read this.
Secondly, since you probably didn't read it, the card you're using probably sucks.
The tl;dr of that article is that the MOMENT you let it get away with speaking for {{user}} it will KEEP DOING IT. This INCLUDES any instances in the initial message and example text. There is no quick and easy way to fix this. You have to go hands on.
Basically, you have to edit all instances of "actions" from {{user}} in the AI message to, instead, "reactions" from {{char}}. e.g.
{{user}} lifted a hand to {{char}}'s cheek and touched them
(user is actively doing something. bad. not good.){{char}} felt {{user}} touch their cheek
(char is reacting to something user is doing. yay! acceptable!)
Boo! that's too much work!! any alternatives? Yes, actually! Find a better card. That's all.
I keep getting straight up nonsense from my bot/it writes too much like Shakespeare on crack.
Decrease your temperature by 0.10 intervals and generate responses until it gets to a readability that you enjoy.
It keeps generating blank messages.
I found that going above a certain Max Context Size will do this. I keep mine around 3.6k for this exact reason
CUDA Error? What's that?
CUDA Error indicates an error with the GPU itself. Not your fault! There's no surefire way to fix this without getting the devs involved, but when it shows up you can either
- Keep swiping until it goes away
- Decrease your max context size
- Wait a bit then come back
Error: character definition too large
This means your character definition total has too many tokens and Mars can't handle it. What does that mean? Well... first, let's answer what tokens are.
What are tokens?
Basically,
more token = more money (Doesn't quite matter for Mars because it uses a flat rate)
more word = more token
Context size = basically how much bot can remember at once, including both permanent and temporary tokens. Overloads when the "character definition is too large," i.e. your bot is eating too many tokens, and Mars is shitting itself because it's too full.
Permanent tokens = run every time you ask bot to generate message. If your bot seems lobotomized and doesn't remember anything you say, it's probably because one of these is eating too many tokens:
- Main prompt/System prompt / Pre-History prompt
- Jailbreak / Post-History prompt
- User persona/appearance
- Character card (description + personality + scenario)
Temporary tokens = things eventually "forgotten" by the bot as the chat develops to allow for more short term memory.
- Chat history
- Example dialogue
- Initial message
i.e. if your bot has a small token count, it will remember more.
Mars is still relatively young as far as LLMs go, but many users have noted so far that "smaller" bots run better. there's no hard guidelines for size, but generally it's a good idea to keep your permanent tokens <1k for Mars. With that out of the way...
The card I am using has too many tokens. What do I do?
Quite honestly, a lot of bots are not well made/optimized. If you really like the gist of a character someone has made but see a lot of "token bloat," you'll likely have to go in there yourself and pull out the weeds for it to run smoothly by overriding the character definitions.
What constitutes a "poorly optimized" bot?
Good question... there are a lot of things, some that can be seen easily at a glance, but some are more egregious and will require more work to get rid of.
First step to diagnosing the card's problems
- Q: Does it have bits like [OOC: {{char}} will not speak for user] or [System note: {{char}} will not speak for user]?
- Those things are usually called jailbreaks, which you already have!
- On chub.venus it's sometimes called the "post history prompt," which, as described above, takes up permanent tokens. What does this mean? well, essentially, you're just adding another jail break that might even conflict with your own, resulting in a weird set of instructions for the AI, as well as token bloat.
- How to fix: just go ahead and cut those parts out.
It still has a huge amount of tokens. What can I do to slim it down more?
-
Q: Is it an established character? Is any of the information widely known? If you ask a layman (someone who just barely knows about the established character) what they know about the character, will they know it? If so, you can get rid of that information.
- e.g. {{char}} is Sonic, and the description reads,
Sonic is a blue hedgehog who can run at the speed of sound and is enemies with Dr. Eggman.
- This information is widely known, so you can actually just shorten that to
{{char}} is Sonic from the Sonic Franchise,
and the bot will go "ah! that Sonic!"
- e.g. {{char}} is Sonic, and the description reads,
- Q: does the information look poorly formatted or even... familiar?
- If you look at it and think, "wait a minute, isn't just a wiki page? Did someone seriously just copy paste it and say "that's a wrap" ? Chances are... Yes, unfortunately. It's a plague upon junior bot makers to do this, which is obviously a lot of token bloat because...
- The information is usually widely known
- A lot of the information is unimportant.
- Try to look through the "wiki entry" type cards to pick out the details you think are actually important... or just find a better made card.
- Q: does all the information actually matter in terms of rp?
- Many botmakers will write things for human eyes, which is, quite honestly, not their fault. its pretty much second nature when writing to write something that is enjoyable to read, but the AI can look at that same information and say, "I don't know what to do with this."
- For example, writing that
{{char}} has black and white checkered pants that are slightly frayed at the ends.
That's for a human eyeball to read, because you're like "wow, imagery!" but the AI is like "why would i need to know this?" because honestly, when will it need to know your character has specificallyblack and white checkered pants that are slightly frayed at the ends
? it takes up permanent tokens, which means it just runs every. single. message. Every Single Message, the card is pushing the bot to remember, "this character hasblack and white checkered pants that are slightly frayed at the ends
." If you have flavor text like this (things that won't come up in rp), you can probably just gut it, unless you're certain it'd be immersion breaking to do so.
- For example, writing that
- Essentially the description section should include things that you think are necessary for it to run every message, things like
{{char}} speaks in a cheerful, uplifting tone, and is always kind to others.
That's serves as a little nudge saying, "hey, remember this when you write dialogue, okay?" - If you know rule "of Chekov's gun," apply it! If you notice that something doesn't come up in rp, delete it. What's it there for if you're not gonna use it?
- Many botmakers will write things for human eyes, which is, quite honestly, not their fault. its pretty much second nature when writing to write something that is enjoyable to read, but the AI can look at that same information and say, "I don't know what to do with this."
How do I use Mars/Can I use Mars on a front-end that isn't chub.venus.ai ?
Absolutely!
Text Guide
- Open https://venus.chub.ai/subscription
- Copy the reverse proxy url, https://mars.chub.ai/chub/asha/v1 , which serves as an OpenAI mimic. This is not OpenAI. It merely serves as a way for Mars to connect to other front-ends by behaving in the same way that OpenAI proxies do.
- Click "New Token" and copy the token it generates. Store it somewhere safe, but no worries if you lose it, you can make a new one.
- Go to the front-end that you desire and insert the reverse proxy url into the reverse proxy field.
- Insert your token as the proxy password and hit save.
- Et voila! You are done.
Visual Guide
Should I get Mars or Mercury? What's the difference between the two?
If you get Mars, you will get access to Mercury as well. If you're not sure whether Mars is worth it, I'd recommend you to check out my log compendium for Mars logs and Mercury logs to compare between the two.
The biggest difference between Mars and Mercury is the parameter size. Mars is 70B whereas Mercury is 13B. "Abstractly, Mercury is a much lighter weight model than Mars. Not as good at logic, worse at memory tasks, but also a very creative writer. Some people prefer it to Mars for certain kinds of roleplay." - quoted from the lovely Joystick_Hero is is much smarter at this sort of thing than I am.
Finance related questions
Varies based on situation, but generally you should message/email one of the devs for this sort of question
Lore
- Email: [email protected]
- Discord: @lloorree
Data
- Email: [email protected]
- Discord: @ddaattaalore
I just paid for Mars and tried using it on the site. It says I don't have tokens, what does this mean?
Basically it means that the servers haven't processed your payment and applied it to your account yet. How long it takes varies, but give it an hour or so if you're having trouble. If you still don't have access, message one of the devs. Make sure to include your chub username, a description of your problem, and proof of purchase.
I'm not happy with the service. Can I get a refund?
Depends on a few things, but the devs have final say, so message them about it
I cancelled my subscription and still got billed. Help?
Message one of the devs about it with a screenshot of your transaction along with an explanation of what happened so they can help you out.
I paid through crypto and I haven't gotten access yet.
The blockchain takes a little while to resolve. Give it a day or two, and if you still don't have access, message one of the devs along with a screenshot of your transaction receipt/proof of payment.
I am unable to pay through crypto or PayPal. Is there another way to pay?
No.
Ok but why....
Fun fact, most payment companies don't like working with sites like chub.ai because of the content hosted there. Stripe used to work with chub but got scared off because of. Y'know. The stuff. It'll probably take a while for new payment options to be added.