---
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-experimental
Using turboderp's ExLlamaV2 experimental for quantization.
Each branch contains an individual bits per weight. This is an experimental ExLlamaV2 quantization with no measurement.json produced.
Default arguments used except when the bits per weight is above 6.0, at that point the lm_head layer is quantized at 8 bits per weight instead of the default 6.
Original model: https://huggingface.co/openaccess-ai-collective/DPOpenHermes-7B-v2
8.0 bits per weight
6.0 bits per weight
5.0 bits per weight
4.0 bits per weight
3.5 bits per weight
## Download instructions
With git:
```shell
git clone --single-branch --branch 4_0 https://huggingface.co/bartowski/DPOpenHermes-7B-v2-experimental-exl2
```
With huggingface hub (credit to TheBloke for instructions):
```shell
pip3 install huggingface-hub
```
To download the `main` (only useful if you only care about measurement.json) branch to a folder called `DPOpenHermes-7B-v2-experimental-exl2`:
```shell
mkdir DPOpenHermes-7B-v2-experimental-exl2
huggingface-cli download bartowski/DPOpenHermes-7B-v2-experimental-exl2 --local-dir DPOpenHermes-7B-v2-experimental-exl2 --local-dir-use-symlinks False
```
To download from a different branch, add the `--revision` parameter:
```shell
mkdir DPOpenHermes-7B-v2-experimental-exl2
huggingface-cli download bartowski/DPOpenHermes-7B-v2-experimental-exl2 --revision 4_0 --local-dir DPOpenHermes-7B-v2-experimental-exl2 --local-dir-use-symlinks False
```