You can deploy this model and start earning money today!

bartowski/
DIBT-Mistral-7B-QLoRA-exl2

Name: DIBT-Mistral-7B-QLoRA-exl2
Availability: InStock

text-generation

Views

No views yet

Exllama v2 Quantizations of DIBT-Mistral-7B-QLoRA

Using turboderp's ExLlamaV2 v0.0.15 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/Locutusque/DIBT-Mistral-7B-QLoRA

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.
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/bartowski/DIBT-Mistral-7B-QLoRA-exl2 DIBT-Mistral-7B-QLoRA-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 DIBT-Mistral-7B-QLoRA-exl2:

shell

mkdir DIBT-Mistral-7B-QLoRA-exl2
huggingface-cli download bartowski/DIBT-Mistral-7B-QLoRA-exl2 --local-dir DIBT-Mistral-7B-QLoRA-exl2 --local-dir-use-symlinks False

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

Linux:

shell

mkdir DIBT-Mistral-7B-QLoRA-exl2-6_5
huggingface-cli download bartowski/DIBT-Mistral-7B-QLoRA-exl2 --revision 6_5 --local-dir DIBT-Mistral-7B-QLoRA-exl2-6_5 --local-dir-use-symlinks False

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

shell

mkdir DIBT-Mistral-7B-QLoRA-exl2-6.5
huggingface-cli download bartowski/DIBT-Mistral-7B-QLoRA-exl2 --revision 6_5 --local-dir DIBT-Mistral-7B-QLoRA-exl2-6.5 --local-dir-use-symlinks False

Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski