bartowski's picture
Add 4.0 link
08aba1c
metadata
tags:
  - llm
  - llama
  - llama2
quantized_by: bartowski
pipeline_tag: text-generation

Exllama v2 Quantizations of Free_Sydney_V2_Mistral_7b

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/FPHam/Free_Sydney_V2_Mistral_7b

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/Free_Sydney_V2_Mistral_7b-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 Free_Sydney_V2_Mistral_7b-exl2:

mkdir Free_Sydney_V2_Mistral_7b-exl2
huggingface-cli download bartowski/Free_Sydney_V2_Mistral_7b-exl2 --local-dir Free_Sydney_V2_Mistral_7b-exl2 --local-dir-use-symlinks False

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

mkdir Free_Sydney_V2_Mistral_7b-exl2
huggingface-cli download bartowski/Free_Sydney_V2_Mistral_7b-exl2 --revision 4_0 --local-dir Free_Sydney_V2_Mistral_7b-exl2 --local-dir-use-symlinks False