Quantization made by Richard Erkhov.

Maidphin-Kunoichi-7B - GGUF

Model creator: https://huggingface.co./nbeerbower/
Original model: https://huggingface.co./nbeerbower/Maidphin-Kunoichi-7B/

Name	Quant method	Size
Maidphin-Kunoichi-7B.Q2_K.gguf	Q2_K	2.53GB
Maidphin-Kunoichi-7B.IQ3_XS.gguf	IQ3_XS	2.81GB
Maidphin-Kunoichi-7B.IQ3_S.gguf	IQ3_S	2.96GB
Maidphin-Kunoichi-7B.Q3_K_S.gguf	Q3_K_S	2.95GB
Maidphin-Kunoichi-7B.IQ3_M.gguf	IQ3_M	3.06GB
Maidphin-Kunoichi-7B.Q3_K.gguf	Q3_K	3.28GB
Maidphin-Kunoichi-7B.Q3_K_M.gguf	Q3_K_M	3.28GB
Maidphin-Kunoichi-7B.Q3_K_L.gguf	Q3_K_L	3.56GB
Maidphin-Kunoichi-7B.IQ4_XS.gguf	IQ4_XS	3.67GB
Maidphin-Kunoichi-7B.Q4_0.gguf	Q4_0	3.83GB
Maidphin-Kunoichi-7B.IQ4_NL.gguf	IQ4_NL	3.87GB
Maidphin-Kunoichi-7B.Q4_K_S.gguf	Q4_K_S	3.86GB
Maidphin-Kunoichi-7B.Q4_K.gguf	Q4_K	4.07GB
Maidphin-Kunoichi-7B.Q4_K_M.gguf	Q4_K_M	4.07GB
Maidphin-Kunoichi-7B.Q4_1.gguf	Q4_1	4.24GB
Maidphin-Kunoichi-7B.Q5_0.gguf	Q5_0	4.65GB
Maidphin-Kunoichi-7B.Q5_K_S.gguf	Q5_K_S	4.65GB
Maidphin-Kunoichi-7B.Q5_K.gguf	Q5_K	4.78GB
Maidphin-Kunoichi-7B.Q5_K_M.gguf	Q5_K_M	4.78GB
Maidphin-Kunoichi-7B.Q5_1.gguf	Q5_1	5.07GB
Maidphin-Kunoichi-7B.Q6_K.gguf	Q6_K	5.53GB
Maidphin-Kunoichi-7B.Q8_0.gguf	Q8_0	7.17GB

Original model description:

license: cc-by-nc-4.0 base_model:

SanjiWatsuki/Kunoichi-DPO-v2-7B
nbeerbower/maidphin library_name: transformers tags:
mergekit
merge

Maidphin-Kunoichi-7B

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: nbeerbower/maidphin
    layer_range: [0, 32]
  - model: SanjiWatsuki/Kunoichi-DPO-v2-7B
    layer_range: [0, 32]
merge_method: slerp
base_model: SanjiWatsuki/Kunoichi-DPO-v2-7B
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
dtype: bfloat16