README.md

---
license: apache-2.0
tags:
- rag
- closed-qa
- context
- mistral
quantized_by: bartowski
pipeline_tag: text-generation
---

## Exllama v2 Quantizations of docsgpt-7b-mistral

Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.0.10">turboderp's ExLlamaV2 v0.0.10</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 VMWareOpenInstruct.parquet as calibration dataset.

Default arguments used except when the bits per weight is above 6.0, at that point the lm_head layer is quantized at 8 bits per weight instead of the default 6.

Original model: https://huggingface.co/Arc53/docsgpt-7b-mistral
 
<a href="https://huggingface.co/bartowski/docsgpt-7b-mistral-exl2/tree/4_0">4.0 bits per weight</a>
 
<a href="https://huggingface.co/bartowski/docsgpt-7b-mistral-exl2/tree/6_0">6.0 bits per weight</a>
 
<a href="https://huggingface.co/bartowski/docsgpt-7b-mistral-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/docsgpt-7b-mistral-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 `docsgpt-7b-mistral-exl2`:

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

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

```shell
mkdir docsgpt-7b-mistral-exl2
huggingface-cli download bartowski/docsgpt-7b-mistral-exl2 --revision 4_0 --local-dir docsgpt-7b-mistral-exl2 --local-dir-use-symlinks False
```