|
--- |
|
license: other |
|
tags: |
|
- llama |
|
- llama-2 |
|
--- |
|
|
|
A 22B model merge by [grimpep](https://huggingface.co/grimpep) mixing [13Bv2-llama-modelmerge](https://huggingface.co/grimpep/13Bv2-llama-modelmerge) with [Wizard-Vicuna-30B-Superhot-8K](https://huggingface.co/TheBloke/Wizard-Vicuna-30B-Superhot-8K-fp16). |
|
<br>Please see the [original repo](https://huggingface.co/grimpep/llama2-22b-wizard_vicuna) for further information.<br><br> |
|
From my brief testing this model works great for chat or roleplaying using Llama2 syntax along with [SimpleProxy](https://github.com/anon998/simple-proxy-for-tavern) or SimpleProxy style prompt instruction. |
