README.md

metadata

license: apache-2.0
datasets:
  - fblgit/tree-of-knowledge
  - Open-Orca/SlimOrca-Dedup
  - allenai/ultrafeedback_binarized_cleaned
library_name: transformers
tags:
  - juanako
  - UNA
  - cybertron
  - fbl
quantized_by: bartowski

Exllama v2 Quantizations of una-cybertron-7b-v2-bf16 at 4.0 bits per weight

Using turboderp's ExLlamaV2 v0.0.10 for quantization.

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

Original model: https://huggingface.co/fblgit/una-cybertron-7b-v2-bf16

Download instructions

With git:

git clone --single-branch --branch 4.0 https://huggingface.co/bartowski/una-cybertron-7b-v2-bf16-exl2

With huggingface hub (credit to TheBloke for instructions):

pip3 install huggingface-hub

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

mkdir una-cybertron-7b-v2-bf16-exl2
huggingface-cli download bartowski/una-cybertron-7b-v2-bf16-exl2 --revision 4_0 --local-dir una-cybertron-7b-v2-bf16-exl2 --local-dir-use-symlinks False