---
license: llama3
---

This is an experimental 2x8B moe with random gates, using the following 2 models

- Hermes-2-Theta-l3-8B by Nous Research https://huggingface.co/NousResearch/Hermes-2-Theta-Llama-3-8B

- llama-3-cat-8B-instruct-V1 by TheSkullery https://huggingface.co/TheSkullery/llama-3-cat-8b-instruct-v1


***Important*** 

Make sure to add `</s>` a stop sequence as it uses llama-3-cat-8B-instruct-V1 as the base model.