Suparious/CerebrumHyperion-7B-DPO-exl2

Exllama v2 Quantizations of hydra-project/CerebrumHyperion-7B-DPO

Using turboderp's ExLlamaV2 v0.0.16 for quantization.

The "main" branch only contains the measurement.json, download one of the other branches for the model (see below)

Each branch contains an individual bits per weight, with the main one containing only the meaurement.json for further conversions.

Original model: https://huggingface.co/hydra-project/CerebrumHyperion-7B-DPO

Branch	Bits	lm_head bits	VRAM (4k)	VRAM (16k)	VRAM (32k)	Description
8_0	8.0	8.0	8.4 GB	9.8 GB	11.8 GB	Maximum quality that ExLlamaV2 can produce, near unquantized performance.
6_5	6.5	8.0	7.2 GB	8.6 GB	10.6 GB	Very similar to 8.0, good tradeoff of size vs performance, recommended.
5_0	5.0	6.0	6.0 GB	7.4 GB	9.4 GB	Slightly lower quality vs 6.5, but usable on 8GB cards.
4_25	4.25	6.0	5.3 GB	6.7 GB	8.7 GB	GPTQ equivalent bits per weight, slightly higher quality.
4_0	4.0	6.0	4.9 GB	6.5 GB	8.5 GB	Just under GPTQ equivalent bits per weight.
3_5	3.5	6.0	4.7 GB	6.1 GB	8.1 GB	Lower quality, only use if you have to.

Download instructions

With git:

git clone --single-branch --branch 6_5 https://huggingface.co/suparious/CerebrumHyperion-7B-DPO-exl2 CerebrumHyperion-7B-DPO-exl2-6_5

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 CerebrumHyperion-7B-DPO-exl2:

mkdir CerebrumHyperion-7B-DPO-exl2
huggingface-cli download suparious/CerebrumHyperion-7B-DPO-exl2 --local-dir CerebrumHyperion-7B-DPO-exl2 --local-dir-use-symlinks False

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

Linux:

mkdir CerebrumHyperion-7B-DPO-exl2-6_5
huggingface-cli download suparious/CerebrumHyperion-7B-DPO-exl2 --revision 6_5 --local-dir CerebrumHyperion-7B-DPO-exl2-6_5 --local-dir-use-symlinks False

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

mkdir CerebrumHyperion-7B-DPO-exl2-6.5
huggingface-cli download suparious/CerebrumHyperion-7B-DPO-exl2 --revision 6_5 --local-dir CerebrumHyperion-7B-DPO-exl2-6.5 --local-dir-use-symlinks False