README.md

---
tags:
- generated_from_trainer
model-index:
- name: zephyr-7b-beta
  results: []
license: mit
datasets:
- HuggingFaceH4/ultrachat_200k
- HuggingFaceH4/ultrafeedback_binarized
language:
- en
base_model: mistralai/Mistral-7B-v0.1
quantized_by: bartowski
---

## Exllama v2 Quantizations of zephyr-7b-beta

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/HuggingFaceH4/zephyr-7b-beta
 
<a href="https://huggingface.co/bartowski/zephyr-7b-beta-exl2/tree/4.0">4.0 bits per weight</a>
 
<a href="https://huggingface.co/bartowski/zephyr-7b-beta-exl2/tree/6.0">6.0 bits per weight</a>
 
<a href="https://huggingface.co/bartowski/zephyr-7b-beta-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/zephyr-7b-beta-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 `zephyr-7b-beta-exl2`:

```shell
mkdir zephyr-7b-beta-exl2
huggingface-cli download bartowski/zephyr-7b-beta-exl2 --local-dir zephyr-7b-beta-exl2 --local-dir-use-symlinks False
```

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

```shell
mkdir zephyr-7b-beta-exl2
huggingface-cli download bartowski/zephyr-7b-beta-exl2 --revision 4.0 --local-dir zephyr-7b-beta-exl2 --local-dir-use-symlinks False
```