README.md

metadata

license: apache-2.0
pipeline_tag: text-generation
tags:
  - finetuned
inference:
  parameters:
    temperature: 0.7
quantized_by: bartowski

Exllama v2 Quantizations of Mistral-7B-Instruct-v0.2 at 7.0 bits per weight

Using turboderp's ExLlamaV2 v0.0.10 for quantization.

Conversion was done using VMWareOpenInstruct.parquet as calibration dataset.

Original model: https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2

Download instructions

With git:

git clone --single-branch --branch 7.0 https://huggingface.co/bartowski/Mistral-7B-Instruct-v0.2-exl2

With huggingface hub (credit to TheBloke for instructions):

pip3 install huggingface-hub

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

mkdir Mistral-7B-Instruct-v0.2-exl2
huggingface-cli download bartowski/Mistral-7B-Instruct-v0.2-exl2 --revision 7_0 --local-dir Mistral-7B-Instruct-v0.2-exl2 --local-dir-use-symlinks False