--- license: cc-by-nc-4.0 --- Re:MythoMax-Mistral (ReMM-Mistral) is a recreation trial of the original [MythoMax-L2-B13](https://huggingface.co/Gryphe/MythoMax-L2-13b) with updated models and data of Mistral. This merge use Gradient merging method to merge ReML-Mistral v2.2 and Huginn. Explaination : ```shell - ReML-Mistral-v2.2: (Chronos-Beluga v2/Hermes/Airboros 2.2.1 + LoRA) => The-Face-Of-Goonery/Chronos-Beluga-v2-13bfp16 => jondurbin/airoboros-l2-13b-2.2 by jondurbin/airoboros-l2-13b-2.2.1 => NousResearch/Nous-Hermes-Llama2-13b => Applying Undi95/llama2-to-mistral-diff at 1.0 at the end With that : - ReMM-Mistral: (ReML-Mistral-v2.2/Huginn) => ReMM by the one above => The-Face-Of-Goonery/Huginn-13b-FP16 ``` ## Description This repo contains fp16 files of ReMM-Mistral, a recreation of the original MythoMax, but updated and merged with Gradient method and Mistral data. ## Models used - [The-Face-Of-Goonery/Chronos-Beluga-v2-13bfp16](https://huggingface.co/The-Face-Of-Goonery/Chronos-Beluga-v2-13bfp16=) - [jondurbin/airoboros-l2-13b-2.2.1](https://huggingface.co/jondurbin/airoboros-l2-13b-2.2.1) - [NousResearch/Nous-Hermes-Llama2-13b](https://huggingface.co/NousResearch/Nous-Hermes-Llama2-13b) - [The-Face-Of-Goonery/Huginn-13b-FP16](https://huggingface.co/The-Face-Of-Goonery/Huginn-13b-FP16) - [Undi95/ReML-Mistral-v2.2-13B](https://huggingface.co/Undi95/ReML-Mistral-v2.2-13B) (Private recreation trial of an updated Mythologic-L2-13B with Mistral data) - [Undi95/llama2-to-mistral-diff](https://huggingface.co/Undi95/llama2-to-mistral-diff) ## Prompt template: Alpaca ``` Below is an instruction that describes a task. Write a response that appropriately completes the request. ### Instruction: {prompt} ### Response: ``` A big thanks to [KoboldAI](https://github.com/KoboldAI/KoboldAI-Client) dev' Henky for giving me a machine powerfull enough to do some of my work! If you want to support me, you can [here](https://ko-fi.com/undiai).