metadata
quantized_by: bartowski
Exllama v2 Quantizations of Antares-11b-v1 at 3.75 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/decapoda-research/Antares-11b-v1
Download instructions
With git:
git clone --single-branch --branch 3.75 https://huggingface.co/bartowski/Antares-11b-v1-exl2
With huggingface hub (credit to TheBloke for instructions):
pip3 install huggingface-hub
To download from a different branch, add the --revision
parameter:
mkdir Antares-11b-v1-exl2
huggingface-cli download bartowski/Antares-11b-v1-exl2 --revision 3_75 --local-dir Antares-11b-v1-exl2 --local-dir-use-symlinks False