Branch	Bits	lm_head bits	VRAM (4k)	VRAM (16k)	VRAM (32k)	Description
8_0	8.0	8.0	8.4 GB	9.2 GB	10.2 GB	Maximum quality that ExLlamaV2 can produce, near unquantized performance.
6_5	6.5	8.0	7.1 GB	7.9 GB	8.9 GB	Very similar to 8.0, good tradeoff of size vs performance, recommended.
5_0	5.0	6.0	5.8 GB	6.6 GB	7.6 GB	Slightly lower quality vs 6.5, but usable on 8GB cards.
4_25	4.25	6.0	5.1 GB	5.9 GB	6.9 GB	GPTQ equivalent bits per weight, slightly higher quality.
3_5	3.5	6.0	4.5 GB	5.3 GB	6.3 GB	Lower quality, only use if you have to.

Download instructions

With git:

git clone --single-branch --branch 6_5 https://huggingface.co/bartowski/dolphincoder-starcoder2-7b-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 dolphincoder-starcoder2-7b-exl2:

shell

mkdir dolphincoder-starcoder2-7b-exl2
huggingface-cli download bartowski/dolphincoder-starcoder2-7b-exl2 --local-dir dolphincoder-starcoder2-7b-exl2 --local-dir-use-symlinks False

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

Linux:

shell

mkdir dolphincoder-starcoder2-7b-exl2-6_5
huggingface-cli download bartowski/dolphincoder-starcoder2-7b-exl2 --revision 6_5 --local-dir dolphincoder-starcoder2-7b-exl2-6_5 --local-dir-use-symlinks False

Windows (which apparently doesn't like _ in folders sometimes?):

shell

mkdir dolphincoder-starcoder2-7b-exl2-6.5
huggingface-cli download bartowski/dolphincoder-starcoder2-7b-exl2 --revision 6_5 --local-dir dolphincoder-starcoder2-7b-exl2-6.5 --local-dir-use-symlinks False