Exllama v2 Quantizations of OpenHermes-2.5-Mistral-7B-16k
Using turboderp's ExLlamaV2 v0.0.8 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.
Original model: https://huggingface.co/NurtureAI/OpenHermes-2.5-Mistral-7B-16k
Download instructions
With git:
git clone --single-branch --branch 4_0 https://huggingface.co/bartowski/OpenHermes-2.5-Mistral-7B-16k-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-Mistral-7B-16k-exl2
:
mkdir OpenHermes-2.5-Mistral-7B-16k-exl2
huggingface-cli download bartowski/OpenHermes-2.5-Mistral-7B-16k-exl2 --local-dir OpenHermes-2.5-Mistral-7B-16k-exl2 --local-dir-use-symlinks False
To download from a different branch, add the --revision
parameter:
mkdir OpenHermes-2.5-Mistral-7B-16k-exl2
huggingface-cli download bartowski/OpenHermes-2.5-Mistral-7B-16k-exl2 --revision 4_0 --local-dir OpenHermes-2.5-Mistral-7B-16k-exl2 --local-dir-use-symlinks False
Model tree for bartowski/OpenHermes-2.5-Mistral-7B-16k-exl2
Base model
mistralai/Mistral-7B-v0.1
Finetuned
this model