README.md

metadata

quantized_by: bartowski

Exllama v2 Quantizations of xDAN-L1-Chat-RL-v1 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/xDAN-AI/xDAN-L1-Chat-RL-v1

Download instructions

With git:

git clone --single-branch --branch 6.0 https://huggingface.co/bartowski/xDAN-L1-Chat-RL-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 xDAN-L1-Chat-RL-v1-exl2
huggingface-cli download bartowski/xDAN-L1-Chat-RL-v1-exl2 --revision 6_0 --local-dir xDAN-L1-Chat-RL-v1-exl2 --local-dir-use-symlinks False