bartowski's picture
measurement.json
634f146 verified
metadata
license: apache-2.0
quantized_by: bartowski
pipeline_tag: text-generation

Exllama v2 Quantizations of KunoichiLake-2x7b

Using turboderp's ExLlamaV2 v0.0.13 for quantization.

The "main" branch only contains the measurement.json, download one of the other branches for the model (see below)

Each branch contains an individual bits per weight, with the main one containing only the meaurement.json for further conversions.

Original model: https://huggingface.co/macadeliccc/KunoichiLake-2x7b

Branch Bits lm_head bits VRAM (4k) VRAM (16k) VRAM (32k) Description
8_0 8.0 8.0 13.7 GB 15.1 GB 17.2 GB Maximum quality that ExLlamaV2 can produce, near unquantized performance.
6_5 6.5 8.0 11.5 GB 12.9 GB 15.0 GB Near unquantized performance at vastly reduced size, recommended.
5_0 5.0 6.0 9.3 GB 10.7 GB 12.8 GB Slightly lower quality vs 6.5, great for 12gb cards with 16k context.
4_25 4.25 6.0 8.2 GB 9.6 GB 11.7 GB GPTQ equivalent bits per weight.
3_5 3.5 6.0 7.0 GB 8.4 GB 10.5 GB Lower quality, not recommended.

Download instructions

With git:

git clone --single-branch --branch 6_5 https://huggingface.co/bartowski/KunoichiLake-2x7b-exl2 KunoichiLake-2x7b-exl2-6_5

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 KunoichiLake-2x7b-exl2:

mkdir KunoichiLake-2x7b-exl2
huggingface-cli download bartowski/KunoichiLake-2x7b-exl2 --local-dir KunoichiLake-2x7b-exl2 --local-dir-use-symlinks False

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

Linux:

mkdir KunoichiLake-2x7b-exl2-6_5
huggingface-cli download bartowski/KunoichiLake-2x7b-exl2 --revision 6_5 --local-dir KunoichiLake-2x7b-exl2-6_5 --local-dir-use-symlinks False

Windows (which apparently doesn't like _ in folders sometimes?):

mkdir KunoichiLake-2x7b-exl2-6.5
huggingface-cli download bartowski/KunoichiLake-2x7b-exl2 --revision 6_5 --local-dir KunoichiLake-2x7b-exl2-6.5 --local-dir-use-symlinks False

Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski