Exllama v2 Quantizations of Starling-LM-7B-beta
Using turboderp's ExLlamaV2 v0.0.16 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/Nexusflow/Starling-LM-7B-beta
Branch | Bits | lm_head bits | VRAM (4k) | VRAM (16k) | VRAM (32k) | Description |
---|---|---|---|---|---|---|
8_0 | 8.0 | 8.0 | 8.4 GB | 9.8 GB | 11.8 GB | Maximum quality that ExLlamaV2 can produce, near unquantized performance. |
6_5 | 6.5 | 8.0 | 7.2 GB | 8.6 GB | 10.6 GB | Very similar to 8.0, good tradeoff of size vs performance, recommended. |
5_0 | 5.0 | 6.0 | 6.0 GB | 7.4 GB | 9.4 GB | Slightly lower quality vs 6.5, but usable on 8GB cards. |
4_25 | 4.25 | 6.0 | 5.3 GB | 6.7 GB | 8.7 GB | GPTQ equivalent bits per weight, slightly higher quality. |
3_5 | 3.5 | 6.0 | 4.7 GB | 6.1 GB | 8.1 GB | Lower quality, only use if you have to. |
Download instructions
With git:
git clone --single-branch --branch 6_5 https://huggingface.co/bartowski/Starling-LM-7B-beta-exl2 Starling-LM-7B-beta-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 Starling-LM-7B-beta-exl2
:
mkdir Starling-LM-7B-beta-exl2
huggingface-cli download bartowski/Starling-LM-7B-beta-exl2 --local-dir Starling-LM-7B-beta-exl2 --local-dir-use-symlinks False
To download from a different branch, add the --revision
parameter:
Linux:
mkdir Starling-LM-7B-beta-exl2-6_5
huggingface-cli download bartowski/Starling-LM-7B-beta-exl2 --revision 6_5 --local-dir Starling-LM-7B-beta-exl2-6_5 --local-dir-use-symlinks False
Windows (which apparently doesn't like _ in folders sometimes?):
mkdir Starling-LM-7B-beta-exl2-6.5
huggingface-cli download bartowski/Starling-LM-7B-beta-exl2 --revision 6_5 --local-dir Starling-LM-7B-beta-exl2-6.5 --local-dir-use-symlinks False
Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski