---
license: apache-2.0
tags:
- finetuned
- Instruct
- code
quantized_by: bartowski
---

## Exllama v2 Quantizations of KAI-7B-Instruct

Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.0.7">turboderp's ExLlamaV2 v0.0.7</a> for quantization.

Each branch contains an individual bits per weight, with the main one containing only the meaurement.json for further conversions.

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

Original model: https://huggingface.co/Keynote-Technology/KAI-7B-Instruct
 
<a href="https://huggingface.co/bartowski/KAI-7B-Instruct-exl2/tree/4.0">4.0 bits per weight</a>
 
<a href="https://huggingface.co/bartowski/KAI-7B-Instruct-exl2/tree/6.0">6.0 bits per weight</a>
 
<a href="https://huggingface.co/bartowski/KAI-7B-Instruct-exl2/tree/8.0">8.0 bits per weight</a>

## Download instructions

With git:

```shell
git clone --single-branch --branch 4.0 https://huggingface.co/bartowski/KAI-7B-Instruct-exl2
```

With huggingface hub (credit to TheBloke for instructions):

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

To download the `main` (only useful if you only care about measurement.json) branch to a folder called `KAI-7B-Instruct-exl2`:

```shell
mkdir KAI-7B-Instruct-exl2
huggingface-cli download bartowski/KAI-7B-Instruct-exl2 --local-dir KAI-7B-Instruct-exl2 --local-dir-use-symlinks False
```

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

```shell
mkdir KAI-7B-Instruct-exl2
huggingface-cli download bartowski/KAI-7B-Instruct-exl2 --revision 4.0 --local-dir KAI-7B-Instruct-exl2 --local-dir-use-symlinks False
```