Exllama v2 Quantizations of Tess-2.0-Yi-34B-200K
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/migtissera/Tess-2.0-Yi-34B-200K
| Branch | Bits | lm_head bits | VRAM (4k) | VRAM (16k) | VRAM (32k) | Description |
|---|---|---|---|---|---|---|
| 8_0 | 8.0 | 8.0 | 34.9 GB | 37.6 GB | 41.6 GB | Max quality producable by ExLlamav2, generally unneeded but maximum performance |
| 6_5 | 6.5 | 8.0 | 28.9 GB | 31.6 GB | 35.6 GB | Near unquantized performance at vastly reduced size, recommended. |
| 5_0 | 5.0 | 8.0 | 22.6 GB | 25.3 GB | 29.3 GB | Very high quality, usable at 4k context on 24GB. |
| 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/Tess-2.0-Yi-34B-200K-exl2 Tess-2.0-Yi-34B-200K-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 Tess-2.0-Yi-34B-200K-exl2:
mkdir Tess-2.0-Yi-34B-200K-exl2
huggingface-cli download bartowski/Tess-2.0-Yi-34B-200K-exl2 --local-dir Tess-2.0-Yi-34B-200K-exl2 --local-dir-use-symlinks False
To download from a different branch, add the --revision parameter:
Linux:
mkdir Tess-2.0-Yi-34B-200K-exl2-6_5
huggingface-cli download bartowski/Tess-2.0-Yi-34B-200K-exl2 --revision 6_5 --local-dir Tess-2.0-Yi-34B-200K-exl2-6_5 --local-dir-use-symlinks False
Windows (which apparently doesn't like _ in folders sometimes?):
mkdir Tess-2.0-Yi-34B-200K-exl2-6.5
huggingface-cli download bartowski/Tess-2.0-Yi-34B-200K-exl2 --revision 6_5 --local-dir Tess-2.0-Yi-34B-200K-exl2-6.5 --local-dir-use-symlinks False
Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski