Exllama v2 Quantizations of OpenZephyrChat
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 VMWareOpenInstruct.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/Fredithefish/OpenZephyrChat
Download instructions
With git:
git clone --single-branch --branch 4_0 https://huggingface.co/bartowski/OpenZephyrChat-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 OpenZephyrChat-exl2:
mkdir OpenZephyrChat-exl2
huggingface-cli download bartowski/OpenZephyrChat-exl2 --local-dir OpenZephyrChat-exl2 --local-dir-use-symlinks False
To download from a different branch, add the --revision parameter:
mkdir OpenZephyrChat-exl2
huggingface-cli download bartowski/OpenZephyrChat-exl2 --revision 4_0 --local-dir OpenZephyrChat-exl2 --local-dir-use-symlinks False
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.