---
license: llama2
language:
- en
---
This is an EXL2 quantized model in 3bpw of [jebcarter/Psyfighter-13B](https://huggingface.co/jebcarter/Psyfighter-13B) using [PIPPA](https://huggingface.co/datasets/jasonkstevens/pippa-llama2-chat/blob/refs%2Fconvert%2Fparquet/default/train/0000.parquet) as the calibration dataset. (I might reupload this or add a new branch with a different version that uses the default calibration dataset instead)

Alpaca and ChatML prompt templates seem to work fine with this model.