Exllama v2 Quantizations of Qwen2.5-Coder-32B-Instruct
Using turboderp's ExLlamaV2 v0.2.3 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./Qwen/Qwen2.5-Coder-32B-Instruct
Download instructions
With git:
git clone --single-branch --branch 6_5 https://huggingface.co./bartowski/Qwen2.5-Coder-32B-Instruct-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 Qwen2.5-Coder-32B-Instruct-exl2:
mkdir Qwen2.5-Coder-32B-Instruct-exl2
huggingface-cli download bartowski/Qwen2.5-Coder-32B-Instruct-exl2 --local-dir Qwen2.5-Coder-32B-Instruct-exl2
To download from a different branch, add the --revision parameter:
Linux:
mkdir Qwen2.5-Coder-32B-Instruct-exl2-6_5
huggingface-cli download bartowski/Qwen2.5-Coder-32B-Instruct-exl2 --revision 6_5 --local-dir Qwen2.5-Coder-32B-Instruct-exl2-6_5
Windows (which apparently doesn't like _ in folders sometimes?):
mkdir Qwen2.5-Coder-32B-Instruct-exl2-6.5
huggingface-cli download bartowski/Qwen2.5-Coder-32B-Instruct-exl2 --revision 6_5 --local-dir Qwen2.5-Coder-32B-Instruct-exl2-6.5
Model tree for bartowski/Qwen2.5-Coder-32B-Instruct-exl2
Base model
Qwen/Qwen2.5-32B