My upload speeds have been cooked and unstable lately.
Realistically I'd need to move to get a better provider.
If you want and you are able to, you can support that endeavor and others here (Ko-fi). I apologize for disrupting your experience.
GGUF-IQ-Imatrix quants for Endevor/InfinityRP-v2-8B.
Back at it!
Lewdiculous: "Personally I still prefer the first version based on Mistral, this one hates asterisks."
These quants have been done after the fixes from llama.cpp/pull/6920.
Use KoboldCpp version 1.64 or higher.
Prompt formatting...
Alpaca prompt format recommended.
A safe starting SillyTavern preset can be found here (simple).
The idea is the same as InfinityRP v1, but this one is Llama 3 with 16k ctx! Have fun...
"You are now in roleplay chat mode. Engage in an endless chat, always with a creative response. Follow lengths very precisely and create paragraphs accurately. Always wait your turn, next actions and responses. Your internal thoughts are wrapped with ` marks."
User Message Prefix = ### Input:
Assistant Message Prefix = ### Response:
System Message Prefix = ### Instruction:
Turn on "Include Names" (optional)
Response: (length = medium) <- [tiny, micro, short, medium, long, enormous, huge, massive, humongous]
