README.md

metadata

license: apache-2.0
quantized_by: bartowski

Exllama v2 Quantizations of OpenHermes-2.5-neural-chat-7b-v3-1-7B at 5.0 bits per weight

Using turboderp's ExLlamaV2 v0.0.9 for quantization.

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

Original model: https://huggingface.co/Weyaxi/OpenHermes-2.5-neural-chat-7b-v3-1-7B

Download instructions

With git:

git clone --single-branch --branch 5.0 https://huggingface.co/bartowski/OpenHermes-2.5-neural-chat-7b-v3-1-7B-exl2

With huggingface hub (credit to TheBloke for instructions):

pip3 install huggingface-hub

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

mkdir OpenHermes-2.5-neural-chat-7b-v3-1-7B-exl2
huggingface-cli download bartowski/OpenHermes-2.5-neural-chat-7b-v3-1-7B-exl2 --revision 5_0 --local-dir OpenHermes-2.5-neural-chat-7b-v3-1-7B-exl2 --local-dir-use-symlinks False