Exllama v2 Quantizations of Zebrafish-7B
Using turboderp's ExLlamaV2 v0.0.17 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/mlabonne/Zebrafish-7B
Branch | Bits | lm_head bits | VRAM (4k) | VRAM (16k) | VRAM (32k) | Description |
---|---|---|---|---|---|---|
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/suparious/Zebrafish-7B-exl2 Zebrafish-7B-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 Zebrafish-7B-exl2
:
mkdir Zebrafish-7B-exl2
huggingface-cli download suparious/Zebrafish-7B-exl2 --local-dir Zebrafish-7B-exl2 --local-dir-use-symlinks False
To download from a different branch, add the --revision
parameter:
Linux:
mkdir Zebrafish-7B-exl2-6_5
huggingface-cli download suparious/Zebrafish-7B-exl2 --revision 6_5 --local-dir Zebrafish-7B-exl2-6_5 --local-dir-use-symlinks False
Windows (which apparently doesn't like _ in folders sometimes?):
mkdir Zebrafish-7B-exl2-6.5
huggingface-cli download suparious/Zebrafish-7B-exl2 --revision 6_5 --local-dir Zebrafish-7B-exl2-6.5 --local-dir-use-symlinks False
Model tree for Suparious/Zebrafish-7B-exl2
Base model
liminerity/M7-7b