|
|
--- |
|
|
quantized_by: bartowski |
|
|
--- |
|
|
|
|
|
# Exllama v2 Quantizations of CodeNinja-1.0-OpenChat-7B at 4.0 bits per weight |
|
|
|
|
|
Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.0.11">turboderp's ExLlamaV2 v0.0.11</a> for quantization. |
|
|
|
|
|
Conversion was done using the default calibration dataset. |
|
|
|
|
|
Original model: https://huggingface.co/beowolx/CodeNinja-1.0-OpenChat-7B |
|
|
|
|
|
## 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 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 |
|
|
``` |
|
|
|
