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

# Exllama v2 Quantizations of DPOpenHermes-7B-v2 at 4.0 bits per weight

Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.0.10">turboderp's ExLlamaV2 v0.0.10</a> 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-v2

## Download instructions

With git:

```shell
git clone --single-branch --branch 4.0 https://huggingface.co/bartowski/DPOpenHermes-7B-v2-exl2
```

With huggingface hub (credit to TheBloke for instructions):

```shell
pip3 install huggingface-hub
```

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

```shell
mkdir DPOpenHermes-7B-v2-exl2
huggingface-cli download bartowski/DPOpenHermes-7B-v2-exl2 --revision 4_0 --local-dir DPOpenHermes-7B-v2-exl2 --local-dir-use-symlinks False
```