Tess-XS-v1.1-exl2 / README.md
bartowski's picture
Quant for 6.0
1ac2f81
metadata
license: apache-2.0
quantized_by: bartowski

Exllama v2 Quantizations of Tess-XS-v1.1 at 6.0 bits per weight

Using turboderp's ExLlamaV2 v0.0.8 for quantization.

Conversion was done using wikitext-103-raw-v1-test.parquet as calibration dataset.

Original model: https://huggingface.co/migtissera/Tess-XS-v1.1

Download instructions

With git:

git clone --single-branch --branch 6.0 https://huggingface.co/bartowski/Tess-XS-v1.1-exl2

With huggingface hub (credit to TheBloke for instructions):

pip3 install huggingface-hub

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

mkdir Tess-XS-v1.1-exl2
huggingface-cli download bartowski/Tess-XS-v1.1-exl2 --revision 6_0 --local-dir Tess-XS-v1.1-exl2 --local-dir-use-symlinks False