Description

This repo contains quantized files of MistRP-Dolphin-7B.

<!-- description end --> <!-- description start -->

Models and loras used

• ehartford/dolphin-2.0-mistral-7b
• Vulkane/120-Days-of-Sodom-LoRA-Mistral-7b
• Undi95/Mistral-pippa-sharegpt-7b-qlora
• lemonilia/LimaRP-Mistral-7B-v0.1

<!-- description end --> <!-- prompt-template start -->

Prompt template: ChatML

This model don't seem to like Mirostats a lot, try with 0 at first.

Json file for context in sillytavern here

Json file for preset/instruction in sillytavern here

EDIT: The Json file seems to not want to be imported, so here is the text to copy paste on each setting here

Custom stopping string: ["</s>", "<|", "\n#", "\n*{{user}} ", "\n\n\n", "["]

The recommanded settings are :

Replace assistant in the line <|im_start|>assistant for something useful in your RP, like "friend", "wife", "narrator"

If you want to support me, you can here.