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/fblgit/una-cybertron-7b-v2-bf16

4.0 bits per weight

5.0 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/una-cybertron-7b-v2-bf16-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 una-cybertron-7b-v2-bf16-exl2:

shell

mkdir una-cybertron-7b-v2-bf16-exl2
huggingface-cli download bartowski/una-cybertron-7b-v2-bf16-exl2 --local-dir una-cybertron-7b-v2-bf16-exl2 --local-dir-use-symlinks False

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

shell

mkdir una-cybertron-7b-v2-bf16-exl2
huggingface-cli download bartowski/una-cybertron-7b-v2-bf16-exl2 --revision 4_0 --local-dir una-cybertron-7b-v2-bf16-exl2 --local-dir-use-symlinks False

bartowski/una-cybertron-7b-v2-exl2

Exllama v2 Quantizations of una-cybertron-7b-v2-bf16

Download instructions

bartowski/
una-cybertron-7b-v2-exl2