Edit model card

Exllama v2 Quantizations of mistral_7b_norobots

Using turboderp's ExLlamaV2 v0.0.8 for quantization.

Each branch contains an individual bits per weight, with the main one containing only the meaurement.json for further conversions.

Conversion was done using wikitext-103-raw-v1-test.parquet as calibration dataset.

Default arguments used except when the bits per weight is above 6.0, at that point the lm_head layer is quantized at 8 bits per weight instead of the default 6.

Original model: https://huggingface.co/TheBloke/mistral_7b_norobots-fp16

4.0 bits per weight

6.0 bits per weight

8.0 bits per weight

Download instructions

With git:

git clone --single-branch --branch 4_0 https://huggingface.co/bartowski/mistral_7b_norobots-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 mistral_7b_norobots-exl2:

mkdir mistral_7b_norobots-exl2
huggingface-cli download bartowski/mistral_7b_norobots-exl2 --local-dir mistral_7b_norobots-exl2 --local-dir-use-symlinks False

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

mkdir mistral_7b_norobots-exl2
huggingface-cli download bartowski/mistral_7b_norobots-exl2 --revision 4_0 --local-dir mistral_7b_norobots-exl2 --local-dir-use-symlinks False
Downloads last month
0
Inference Examples
Inference API (serverless) has been turned off for this model.

Model tree for bartowski/mistral_7b_norobots-exl2

Adapter
(5)
this model

Dataset used to train bartowski/mistral_7b_norobots-exl2