Newton-7B-exl2

Exllama v2 Quantizations of Newton-7B

Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.0.12">turboderp's ExLlamaV2 v0.0.12</a> 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/Weyaxi/Newton-7B

Download instructions

With git:

git clone --single-branch --branch 6_5 https://huggingface.co/bartowski/Newton-7B-exl2 Newton-7B-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 Newton-7B-exl2:

mkdir Newton-7B-exl2
huggingface-cli download bartowski/Newton-7B-exl2 --local-dir Newton-7B-exl2 --local-dir-use-symlinks False

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

Linux:

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

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

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

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