README.md

metadata

license: apache-2.0
base_model: mistralai/Mistral-7B-v0.1
datasets:
  - ehartford/dolphin
  - jondurbin/airoboros-2.2.1
language:
  - en
quantized_by: bartowski

Exllama v2 Quantizations of dolphin-2.2.1-mistral-7b at 6.0

Using turboderp's ExLlamaV2 v0.0.7 for quantization.

Conversion was done using wikitext.parquet as calibration dataset.

Original model: https://huggingface.co./ehartford/dolphin-2.2.1-mistral-7b

Download instructions

With git:

git clone --single-branch --branch 6.0 https://huggingface.co./bartowski/dolphin-2.2.1-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 dolphin-2.2.1-mistral-7b-exl2
huggingface-cli download bartowski/dolphin-2.2.1-mistral-7b-exl2 --revision  --local-dir dolphin-2.2.1-mistral-7b-exl2 --local-dir-use-symlinks False