---
license: cc-by-nc-4.0
language:
- en
pipeline_tag: text-generation
quantized_by: bartowski
---

# Exllama v2 Quantizations of NeuralPivot-Mistral-13B at 3.75 bits per weight

Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.0.10">turboderp's ExLlamaV2 v0.0.10</a> for quantization.

Conversion was done using wikitext-103-raw-v1-test.parquet as calibration dataset.

Original model: https://huggingface.co/athirdpath/NeuralPivot-Mistral-13B

## Download instructions

With git:

```shell
git clone --single-branch --branch 3.75 https://huggingface.co/bartowski/NeuralPivot-Mistral-13B-exl2
```

With huggingface hub (credit to TheBloke for instructions):

```shell
pip3 install huggingface-hub
```

To download from a different branch, add the `--revision` parameter:

```shell
mkdir NeuralPivot-Mistral-13B-exl2
huggingface-cli download bartowski/NeuralPivot-Mistral-13B-exl2 --revision 3_75 --local-dir NeuralPivot-Mistral-13B-exl2 --local-dir-use-symlinks False
```