README.md

---
license: llama2
quantized_by: bartowski
pipeline_tag: text-generation
---

## Exllama v2 Quantizations of XwinCoder-13B

Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.0.8">turboderp's ExLlamaV2 v0.0.8</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 Evol-Instruct-Code-80k-v1.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/Xwin-LM/XwinCoder-13B
 
<a href="https://huggingface.co/bartowski/XwinCoder-13B-exl2/tree/3_75">3.75 bits per weight</a>
 
<a href="https://huggingface.co/bartowski/XwinCoder-13B-exl2/tree/4_0">4.0 bits per weight</a>
 
<a href="https://huggingface.co/bartowski/XwinCoder-13B-exl2/tree/6_0">6.0 bits per weight</a>
 
<a href="https://huggingface.co/bartowski/XwinCoder-13B-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/XwinCoder-13B-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 `XwinCoder-13B-exl2`:

```shell
mkdir XwinCoder-13B-exl2
huggingface-cli download bartowski/XwinCoder-13B-exl2 --local-dir XwinCoder-13B-exl2 --local-dir-use-symlinks False
```

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

```shell
mkdir XwinCoder-13B-exl2
huggingface-cli download bartowski/XwinCoder-13B-exl2 --revision 4_0 --local-dir XwinCoder-13B-exl2 --local-dir-use-symlinks False
```