bartowski's picture
Quant for 5.0
aa99dbb
|
raw
history blame
1.01 kB
metadata
license: apache-2.0
language:
  - en
tags:
  - mistral
  - instruct
  - finetune
  - chatml
  - gpt4
quantized_by: bartowski

Exllama v2 Quantizations of Autolycus-Mistral_7B at 8.0,6.0,5.0,4.25,4.0,3.75

Using turboderp's ExLlamaV2 v0.0.7 for quantization.

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

Original model: https://huggingface.co/FPHam/Autolycus-Mistral_7B

Download instructions

With git:

git clone --single-branch --branch 8.0,6.0,5.0,4.25,4.0,3.75 https://huggingface.co/bartowski/Autolycus-Mistral_7B-exl2

With huggingface hub (credit to TheBloke for instructions):

pip3 install huggingface-hub

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

mkdir Autolycus-Mistral_7B-exl2
huggingface-cli download bartowski/Autolycus-Mistral_7B-exl2 --revision  --local-dir Autolycus-Mistral_7B-exl2 --local-dir-use-symlinks False