metadata

license: apache-2.0
quantized_by: bartowski

Exllama v2 Quantizations of neural-chat-7b-v3-3 at 8.0 bits per weight

Using turboderp's ExLlamaV2 v0.0.10 for quantization.

Conversion was done using VMWareOpenInstruct.parquet as calibration dataset.

Original model: https://huggingface.co/Intel/neural-chat-7b-v3-3

Download instructions

With git:

git clone --single-branch --branch 8.0 https://huggingface.co/bartowski/neural-chat-7b-v3-3-exl2

With huggingface hub (credit to TheBloke for instructions):

pip3 install huggingface-hub

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

mkdir neural-chat-7b-v3-3-exl2
huggingface-cli download bartowski/neural-chat-7b-v3-3-exl2 --revision 8_0 --local-dir neural-chat-7b-v3-3-exl2 --local-dir-use-symlinks False