README.md

metadata

license: llama2
quantized_by: bartowski

Exllama v2 Quantizations of LLaMA2-13B-TiefighterLR at 4.25

Using turboderp's ExLlamaV2 v0.0.7 for quantization.

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

Original model: https://huggingface.co/KoboldAI/LLaMA2-13B-TiefighterLR

Download instructions

With git:

git clone --single-branch --branch 4.25 https://huggingface.co/bartowski/LLaMA2-13B-TiefighterLR-exl2

With huggingface hub (credit to TheBloke for instructions):

pip3 install huggingface-hub

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

mkdir LLaMA2-13B-TiefighterLR-exl2
huggingface-cli download bartowski/LLaMA2-13B-TiefighterLR-exl2 --revision  --local-dir LLaMA2-13B-TiefighterLR-exl2 --local-dir-use-symlinks False