metadata

quantized_by: bartowski

Exllama v2 Quantizations of Panda-7B-v0.1 at 3.5 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/NeuralNovel/Panda-7B-v0.1

Download instructions

With git:

git clone --single-branch --branch 3.5 https://huggingface.co/bartowski/Panda-7B-v0.1-exl2

With huggingface hub (credit to TheBloke for instructions):

pip3 install huggingface-hub

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

mkdir Panda-7B-v0.1-exl2
huggingface-cli download bartowski/Panda-7B-v0.1-exl2 --revision 3_5 --local-dir Panda-7B-v0.1-exl2 --local-dir-use-symlinks False