metadata

tags:
  - generated_from_trainer
model-index:
  - name: zephyr-7b-beta
    results: []
license: mit
datasets:
  - HuggingFaceH4/ultrachat_200k
  - HuggingFaceH4/ultrafeedback_binarized
language:
  - en
base_model: mistralai/Mistral-7B-v0.1
quantized_by: bartowski

Exllama v2 Quantizations of zephyr-7b-beta at 4.0

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/HuggingFaceH4/zephyr-7b-beta

Download instructions

With git:

git clone --single-branch --branch 4.0 https://huggingface.co/bartowski/zephyr-7b-beta-exl2

With huggingface hub (credit to TheBloke for instructions):

pip3 install huggingface-hub

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

mkdir zephyr-7b-beta-exl2
huggingface-cli download bartowski/zephyr-7b-beta-exl2 --revision  --local-dir zephyr-7b-beta-exl2 --local-dir-use-symlinks False