Downloads · 30 days
5
8% of all-time downloads
JayhC/kuno-kunoichi-v1-DPO-v2-SLERP-7B-8bpw-h8-exl2-rpcal
kuno-kunoichi-v1-DPO-v2-SLERP-7B-8bpw-h8-exl2-rpcal is a text generation model from JayhC. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as cc-by-nc-4.0.
<br/<br/ 8bpw/h8 exl2 quantization of grimjim/kuno-kunoichi-v1-DPO-v2-SLERP-7B using PIPPA calibration dataset.
Downloads · 30 days
5
8% of all-time downloads
All-time downloads
64
Public
Repo size
7.4 GB
Likes
0
Public
Click a slice to open those files.
.safetensors7.4 GB · 100%
From the Hugging Face model README
<br/><br/> 8bpw/h8 exl2 quantization of grimjim/kuno-kunoichi-v1-DPO-v2-SLERP-7B using PIPPA calibration dataset.
ORIGINAL CARD:
kuno-kunoichi-v1-DPO-v2-SLERP-7B is a merge of pre-trained language models created using mergekit. I'm hoping that the result is more robust against errors or when merging due to "denseness", as the two models likely implement comparable reasoning at least somewhat differently.
I've performed some testing with ChatML format prompting using temperature=1.1 and minP=0.03. The model also supports Alpaca format prompts.
GGUF-IQ-Imatrix quants helpfully provided by Lewdiculous.
This model was merged using the SLERP merge method.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
slices:
- sources:
- model: SanjiWatsuki/Kunoichi-7B
layer_range: [0,32]
- model: SanjiWatsuki/Kunoichi-DPO-v2-7B
layer_range: [0,32]
merge_method: slerp
base_model: SanjiWatsuki/Kunoichi-7B
parameters:
t:
- value: 0.5
dtype: float16