Hi guys
I'm just here to keep you updated about my guides
since i'm retired, i was not updating my guides anymore, but people kept asking me about them and and asking for help
So i decided to update them

Here's my guides:

https://rentry.co/KOpenRouterJanitorProxyGuide

https://rentry.co/KChutesAIProxyGuide

https://rentry.co/KSillyTavernGuide

I'll give you guys a quick changelog:

- openrouter and chutes guides now match the new janitor proxy configuration template

- updated recommended models on both guides

- updated chutes' models prices (chutes has no good free models anymore (Besides gemma))

- updated chutes' subscription prices (you can't use chutes for free anymore)

- updated guides' links

- more things that i probably forgot

✦. ─────────୨ৎ───────── .✦

My Discord Server

⭐BE A SUPPORTER!⭐

I may be retired, but i still make bots!

Support me and enjoy the many benefits! See the list of subscriptions here.

You can either subscribe in my Ko-Fi and my Patreon page.

Or, if you don't want any benefits, you can just donate a random amount in my Ko-Fi.

Also, thank you to everyone who has supported me so far!

✦. ─────────୨ৎ───────── .✦

⭐ MY RECOMENDATIONS ⭐

▶ Generation Settings:

Temperature: 1

I had several problems like LLM repeating the same sentences all the time when the temperature was below 1. At the same time, it generates unreadable and very bizarre texts when it is above. JLLM rarely presents problems at temperature 1 so that is the value I most recommend.

Max tokens: 0

I've noticed that it's very rare for JLLM to write more than 400 tokens, even with the limit set to 0. So if you'd rather make sure that LLM doesn't write too much in any given situation, I'd suggest setting the limit to 400 or less, depending on your taste, but it's possible that LLM will leave some text unfinished. If you're like me and don't care too much, leave it at 0.

Proxy: See my Openrouter proxy guide | Or my ChutesAI proxy guide

Free Proxies for us humble folks! If you want to know how to use proxies, use my guides or join my discord server and ask me.

Those proxies have much more context memory, which makes it immensely more interesting than our dear JLLM. If there are models that I would recommend, are these ones.