Exllama v2 Quantizations of Hyperion-3.0-Yi-34B
Using turboderp's ExLlamaV2 v0.0.15 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/Locutusque/Hyperion-3.0-Yi-34B
| Branch | Bits | lm_head bits | VRAM (4k) | VRAM (16k) | VRAM (32k) | Description |
|---|---|---|---|---|---|---|
| 6_5 | 6.5 | 8.0 | 28.9 GB | 31.6 GB | 35.6 GB | Near unquantized performance at vastly reduced size, recommended. |
| 4_25 | 4.25 | 6.0 | 19.5 GB | 22.2 GB | 26.2 GB | GPTQ equivalent bits per weight, slightly higher quality. |
| 3_5 | 3.5 | 6.0 | 16.5 GB | 19.2 GB | 23.2 GB | Lower quality, only use if you have to. |
| 3_0 | 3.0 | 6.0 | 14.3 GB | 17.0 GB | 21.0 GB | Very low quality, usable with 16gb of VRAM. |
Download instructions
With git:
git clone --single-branch --branch 6_5 https://huggingface.co/bartowski/Hyperion-3.0-Yi-34B-exl2 Hyperion-3.0-Yi-34B-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 Hyperion-3.0-Yi-34B-exl2:
mkdir Hyperion-3.0-Yi-34B-exl2
huggingface-cli download bartowski/Hyperion-3.0-Yi-34B-exl2 --local-dir Hyperion-3.0-Yi-34B-exl2 --local-dir-use-symlinks False
To download from a different branch, add the --revision parameter:
Linux:
mkdir Hyperion-3.0-Yi-34B-exl2-6_5
huggingface-cli download bartowski/Hyperion-3.0-Yi-34B-exl2 --revision 6_5 --local-dir Hyperion-3.0-Yi-34B-exl2-6_5 --local-dir-use-symlinks False
Windows (which apparently doesn't like _ in folders sometimes?):
mkdir Hyperion-3.0-Yi-34B-exl2-6.5
huggingface-cli download bartowski/Hyperion-3.0-Yi-34B-exl2 --revision 6_5 --local-dir Hyperion-3.0-Yi-34B-exl2-6.5 --local-dir-use-symlinks False
Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski