Special thanks to Charles Goddard for the conversion script to create llama models from internlm

Exllama v2 Quantizations of internlm2-20b-llama

Using turboderp's ExLlamaV2 v0.0.11 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.

Conversion was done using the default 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/internlm/internlm2-20b

Download instructions

With git:

git clone --single-branch --branch 4_0 https://huggingface.co/bartowski/internlm2-20b-llama-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 internlm2-20b-llama-exl2:

mkdir internlm2-20b-llama-exl2
huggingface-cli download bartowski/internlm2-20b-llama-exl2 --local-dir internlm2-20b-llama-exl2 --local-dir-use-symlinks False

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

mkdir internlm2-20b-llama-exl2
huggingface-cli download bartowski/internlm2-20b-llama-exl2 --revision 4_0 --local-dir internlm2-20b-llama-exl2 --local-dir-use-symlinks False