Edit model card

Exllama v2 Quantizations of gemma-7b-openhermes

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.

Original model: https://huggingface.co/abideen/gemma-7b-openhermes

No GQA - VRAM requirements will be higher

Branch Bits lm_head bits Size (4k) Size (16k) Description
8_0 8.0 8.0 14.0 GB 19.4 GB Maximum quality that ExLlamaV2 can produce, near unquantized performance.
6_5 6.5 8.0 12.5 GB 17.9 GB Near unquantized performance at vastly reduced size, recommended.
5_0 5.0 6.0 10.9 GB 16.3 GB Slightly lower quality vs 6.5, great for 12GB cards with 4k context.
4_25 4.25 6.0 10.2 GB 15.7 GB GPTQ equivalent bits per weight, ideal for 16GB cards at 16k context
3_5 3.5 6.0 9.5 GB 14.9 GB Lower quality, not recommended.

Download instructions

With git:

git clone --single-branch --branch 6_5 https://huggingface.co/bartowski/gemma-7b-openhermes-exl2 gemma-7b-openhermes-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 gemma-7b-openhermes-exl2:

mkdir gemma-7b-openhermes-exl2
huggingface-cli download bartowski/gemma-7b-openhermes-exl2 --local-dir gemma-7b-openhermes-exl2 --local-dir-use-symlinks False

To download from a different branch, add the --revision parameter:

Linux:

mkdir gemma-7b-openhermes-exl2-6_5
huggingface-cli download bartowski/gemma-7b-openhermes-exl2 --revision 6_5 --local-dir gemma-7b-openhermes-exl2-6_5 --local-dir-use-symlinks False

Windows (which apparently doesn't like _ in folders sometimes?):

mkdir gemma-7b-openhermes-exl2-6.5
huggingface-cli download bartowski/gemma-7b-openhermes-exl2 --revision 6_5 --local-dir gemma-7b-openhermes-exl2-6.5 --local-dir-use-symlinks False

Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski

Downloads last month
0

Finetuned from

Dataset used to train bartowski/gemma-7b-openhermes-exl2