bartowski's picture
Quant for 6.0
923f380
|
raw
history blame
917 Bytes
metadata
quantized_by: bartowski

Exllama v2 Quantizations of ToxicHermes-2.5-Mistral-7B at 6.0 bits per weight

Using turboderp's ExLlamaV2 v0.0.11 for quantization.

Conversion was done using the default calibration dataset.

Original model: https://huggingface.co/joey00072/ToxicHermes-2.5-Mistral-7B

Download instructions

With git:

git clone --single-branch --branch 6.0 https://huggingface.co/bartowski/ToxicHermes-2.5-Mistral-7B-exl2

With huggingface hub (credit to TheBloke for instructions):

pip3 install huggingface-hub

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

mkdir ToxicHermes-2.5-Mistral-7B-exl2
huggingface-cli download bartowski/ToxicHermes-2.5-Mistral-7B-exl2 --revision 6_0 --local-dir ToxicHermes-2.5-Mistral-7B-exl2 --local-dir-use-symlinks False