--- license: cc-by-nc-4.0 tags: - not-for-all-audiences - nsfw --- ## Description This repo contains fp16 files of MistRP-Dolphin-7B. ## Models and loras used - [Open-Orca/Mistral-7B-OpenOrca](https://huggingface.co/Open-Orca/Mistral-7B-OpenOrca) - [Vulkane/120-Days-of-Sodom-LoRA-Mistral-7b](https://huggingface.co/Vulkane/120-Days-of-Sodom-LoRA-Mistral-7b) - [Undi95/Mistral-pippa-sharegpt-7b-qlora](https://huggingface.co/Undi95/Mistral-pippa-sharegpt-7b-qlora) - [lemonilia/LimaRP-Mistral-7B-v0.1](https://huggingface.co/lemonilia/LimaRP-Mistral-7B-v0.1) ## 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](https://files.catbox.moe/ejrfbf.json) Json file for preset/instruction in sillytavern [here](https://files.catbox.moe/kdezni.json) EDIT: The Json file seems to not want to be imported, so here is the text to copy paste on each setting [here](https://pastebin.com/QDb88z2u) ```shell Custom stopping string: ["", "<|", "\n#", "\n*{{user}} ", "\n\n\n", "["] ``` The recommanded settings are : ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63ab1241ad514ca8d1430003/vwllTNOgqgQr2VySloCdo.png) 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](https://ko-fi.com/undiai).