metadata
quantized_by: bartowski
Exllama v2 Quantizations of bagel-dpo-34b-v0.2 at 3.0 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/jondurbin/bagel-dpo-34b-v0.2
Download instructions
With git:
git clone --single-branch --branch 3.0 https://huggingface.co/bartowski/bagel-dpo-34b-v0.2-exl2
With huggingface hub (credit to TheBloke for instructions):
pip3 install huggingface-hub
To download from a different branch, add the --revision
parameter:
mkdir bagel-dpo-34b-v0.2-exl2
huggingface-cli download bartowski/bagel-dpo-34b-v0.2-exl2 --revision 3_0 --local-dir bagel-dpo-34b-v0.2-exl2 --local-dir-use-symlinks False