metadata

base_model: teknium/OpenHermes-2.5-Mistral-7B
license: apache-2.0
datasets:
  - teknium/openhermes
  - argilla/ultrafeedback-binarized-preferences
  - Intel/orca_dpo_pairs
language:
  - en
library_name: transformers
pipeline_tag: text-generation
quantized_by: bartowski

Exllama v2 Quantizations of DPOpenHermes-7B at 6.0 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/openaccess-ai-collective/DPOpenHermes-7B

Download instructions

With git:

git clone --single-branch --branch 6.0 https://huggingface.co/bartowski/DPOpenHermes-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 DPOpenHermes-7B-exl2
huggingface-cli download bartowski/DPOpenHermes-7B-exl2 --revision 6_0 --local-dir DPOpenHermes-7B-exl2 --local-dir-use-symlinks False