metadata
license: apache-2.0
language:
- en
tags:
- moe
- merge
quantized_by: bartowski
pipeline_tag: text-generation
Exllama v2 Quantizations of Buttercup-4x7B-V2-laser
Using turboderp's ExLlamaV2 v0.0.13 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.
| Branch | Bits | lm_head bits | VRAM (4k) | VRAM (16k) | VRAM (32k) | Description |
|---|---|---|---|---|---|---|
| 8_0 | 8.0 | 8.0 | 24.8 GB | 26.3 GB | 28.3 GB | Maximum quality that ExLlamaV2 can produce, near unquantized performance. |
| 6_5 | 6.5 | 8.0 | 20.3 GB | 21.8 GB | 23.8 GB | Near unquantized performance at vastly reduced size, recommended. |
| 5_0 | 5.0 | 6.0 | 15.8 GB | 17.3 GB | 19.3 GB | Slightly lower quality vs 6.5. |
| 4_25 | 4.25 | 6.0 | 14.0 GB | 15.5 GB | 17.5 GB | GPTQ equivalent bits per weight, slightly higher quality, great for 16gb cards with 16k context. |
| 3_5 | 3.5 | 6.0 | 11.3 GB | 12.8 GB | 14.8 GB | Lower quality, not recommended, only suitable for 12GB cards. |
Download instructions
With git:
git clone --single-branch --branch 6_5 https://huggingface.co/bartowski/Buttercup-4x7B-V2-laser-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 Buttercup-4x7B-V2-laser-exl2:
mkdir Buttercup-4x7B-V2-laser-exl2
huggingface-cli download bartowski/Buttercup-4x7B-V2-laser-exl2 --local-dir Buttercup-4x7B-V2-laser-exl2 --local-dir-use-symlinks False
To download from a different branch, add the --revision parameter:
Linux:
mkdir Buttercup-4x7B-V2-laser-exl2-6_5
huggingface-cli download bartowski/Buttercup-4x7B-V2-laser-exl2 --revision 6_5 --local-dir Buttercup-4x7B-V2-laser-exl2-6_5 --local-dir-use-symlinks False
Windows (which apparently doesn't like _ in folders sometimes?):
mkdir Buttercup-4x7B-V2-laser-exl2-6.5
huggingface-cli download bartowski/Buttercup-4x7B-V2-laser-exl2 --revision 6_5 --local-dir Buttercup-4x7B-V2-laser-exl2-6.5 --local-dir-use-symlinks False