bartowski/XwinCoder-34B-exl2

Exllama v2 Quantizations of XwinCoder-34B

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 Evol-Instruct-Code-80k-v1.parquet as calibration dataset.

Original model: https://huggingface.co/Xwin-LM/XwinCoder-34B

3.75 bits per weight

4.0 bits per weight

4.25 bits per weight

4.5 bits per weight

5.0 bits per weight

6.0 bits per weight

Download instructions

With git:

git clone --single-branch --branch 4_0 https://huggingface.co/bartowski/XwinCoder-34B-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 XwinCoder-34B-exl2:

mkdir XwinCoder-34B-exl2
huggingface-cli download bartowski/XwinCoder-34B-exl2 --local-dir XwinCoder-34B-exl2 --local-dir-use-symlinks False

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

mkdir XwinCoder-34B-exl2
huggingface-cli download bartowski/XwinCoder-34B-exl2 --revision 4_0 --local-dir XwinCoder-34B-exl2 --local-dir-use-symlinks False