Exllama v2 Quantizations of OpenHermes-2.5-neural-chat-7b-v3-2-7B
Using turboderp's ExLlamaV2 v0.0.10 for quantization.
Each branch contains an individual bits per weight, with the main one containing only the meaurement.json for further conversions.
Conversion was done using wikitext-103-raw-v1-test.parquet as calibration dataset.
Default arguments used except when the bits per weight is above 6.0, at that point the lm_head layer is quantized at 8 bits per weight instead of the default 6.
Original model: https://huggingface.co/Weyaxi/OpenHermes-2.5-neural-chat-7b-v3-2-7B
Download instructions
With git:
git clone --single-branch --branch 4_0 https://huggingface.co/bartowski/OpenHermes-2.5-neural-chat-7b-v3-2-7B-exl2
With huggingface hub (credit to TheBloke for instructions):
pip3 install huggingface-hub
To download the main (only useful if you only care about measurement.json) branch to a folder called OpenHermes-2.5-neural-chat-7b-v3-2-7B-exl2:
mkdir OpenHermes-2.5-neural-chat-7b-v3-2-7B-exl2
huggingface-cli download bartowski/OpenHermes-2.5-neural-chat-7b-v3-2-7B-exl2 --local-dir OpenHermes-2.5-neural-chat-7b-v3-2-7B-exl2 --local-dir-use-symlinks False
To download from a different branch, add the --revision parameter:
mkdir OpenHermes-2.5-neural-chat-7b-v3-2-7B-exl2
huggingface-cli download bartowski/OpenHermes-2.5-neural-chat-7b-v3-2-7B-exl2 --revision 4_0 --local-dir OpenHermes-2.5-neural-chat-7b-v3-2-7B-exl2 --local-dir-use-symlinks False