README.md

---
license: mit
datasets:
- glaiveai/glaive-code-assistant-v2
- TokenBender/code_instructions_122k_alpaca_style
language:
- en
metrics:
- code_eval
pipeline_tag: text-generation
tags:
- code
- text-generation-inference
quantized_by: bartowski
---

## Exllama v2 Quantizations of CodeNinja-1.0-OpenChat-7B

Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.0.11">turboderp's ExLlamaV2 v0.0.11</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 the default 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/beowolx/CodeNinja-1.0-OpenChat-7B
 
<a href="https://huggingface.co/bartowski/CodeNinja-1.0-OpenChat-7B-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/CodeNinja-1.0-OpenChat-7B-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 `CodeNinja-1.0-OpenChat-7B-exl2`:

```shell
mkdir CodeNinja-1.0-OpenChat-7B-exl2
huggingface-cli download bartowski/CodeNinja-1.0-OpenChat-7B-exl2 --local-dir CodeNinja-1.0-OpenChat-7B-exl2 --local-dir-use-symlinks False
```

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

```shell
mkdir CodeNinja-1.0-OpenChat-7B-exl2
huggingface-cli download bartowski/CodeNinja-1.0-OpenChat-7B-exl2 --revision 4_0 --local-dir CodeNinja-1.0-OpenChat-7B-exl2 --local-dir-use-symlinks False
```