Orca-2-7b-exl2 / README.md
bartowski's picture
Add 4.0 link
e99c61d
metadata
pipeline_tag: text-generation
tags:
  - orca
  - orca2
  - microsoft
quantized_by: bartowski

Exllama v2 Quantizations of Orca-2-7b

Using turboderp's ExLlamaV2 v0.0.8 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.

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/microsoft/Orca-2-7b

4.0 bits per weight

6.0 bits per weight

8.0 bits per weight

Download instructions

With git:

git clone --single-branch --branch 4_0 https://huggingface.co/bartowski/Orca-2-7b-exl2

With huggingface hub (credit to TheBloke for instructions):

pip3 install huggingface-hub

To download the main (only useful if you only care about measurement.json) branch to a folder called Orca-2-7b-exl2:

mkdir Orca-2-7b-exl2
huggingface-cli download bartowski/Orca-2-7b-exl2 --local-dir Orca-2-7b-exl2 --local-dir-use-symlinks False

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

mkdir Orca-2-7b-exl2
huggingface-cli download bartowski/Orca-2-7b-exl2 --revision 4_0 --local-dir Orca-2-7b-exl2 --local-dir-use-symlinks False