Name	Quant method	Size
L3-Evil-Stheno-v3.2-8B.Q2_K.gguf	Q2_K	2.96GB
L3-Evil-Stheno-v3.2-8B.IQ3_XS.gguf	IQ3_XS	3.28GB
L3-Evil-Stheno-v3.2-8B.IQ3_S.gguf	IQ3_S	3.43GB
L3-Evil-Stheno-v3.2-8B.Q3_K_S.gguf	Q3_K_S	3.41GB
L3-Evil-Stheno-v3.2-8B.IQ3_M.gguf	IQ3_M	3.52GB
L3-Evil-Stheno-v3.2-8B.Q3_K.gguf	Q3_K	3.74GB
L3-Evil-Stheno-v3.2-8B.Q3_K_M.gguf	Q3_K_M	3.74GB
L3-Evil-Stheno-v3.2-8B.Q3_K_L.gguf	Q3_K_L	4.03GB
L3-Evil-Stheno-v3.2-8B.IQ4_XS.gguf	IQ4_XS	4.18GB
L3-Evil-Stheno-v3.2-8B.Q4_0.gguf	Q4_0	4.34GB
L3-Evil-Stheno-v3.2-8B.IQ4_NL.gguf	IQ4_NL	4.38GB
L3-Evil-Stheno-v3.2-8B.Q4_K_S.gguf	Q4_K_S	4.37GB
L3-Evil-Stheno-v3.2-8B.Q4_K.gguf	Q4_K	4.58GB
L3-Evil-Stheno-v3.2-8B.Q4_K_M.gguf	Q4_K_M	4.58GB
L3-Evil-Stheno-v3.2-8B.Q4_1.gguf	Q4_1	4.78GB
L3-Evil-Stheno-v3.2-8B.Q5_0.gguf	Q5_0	5.21GB
L3-Evil-Stheno-v3.2-8B.Q5_K_S.gguf	Q5_K_S	5.21GB
L3-Evil-Stheno-v3.2-8B.Q5_K.gguf	Q5_K	5.34GB
L3-Evil-Stheno-v3.2-8B.Q5_K_M.gguf	Q5_K_M	5.34GB
L3-Evil-Stheno-v3.2-8B.Q5_1.gguf	Q5_1	5.65GB
L3-Evil-Stheno-v3.2-8B.Q6_K.gguf	Q6_K	6.14GB
L3-Evil-Stheno-v3.2-8B.Q8_0.gguf	Q8_0	7.95GB

Original model description:

base_model: [] library_name: transformers tags:

mergekit
merge

model

Unleash her demons... Merged the best roleplay model with the best uncensored model to date. The outputs are quite good and verbose.

merge

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

Merge Details

Merge Method

This model was merged using the DARE TIES merge method using Sao10K/L3-8B-Stheno-v3.2 as a base.

Models Merged

The following models were included in the merge:

mlabonne/Daredevil-8B-abliterated

Configuration

The following YAML configuration was used to produce this model:

yaml

models:
  - model: /root/progs/auto-ollama/scripts/Daredevil-8B-abliterated
    parameters:
      density: [1, 0.7, 0.1] # density gradient
      weight: 1.0
merge_method: dare_ties
base_model: /root/progs/auto-ollama/scripts/L3-8B-Stheno-v3.2
parameters:
  normalize: true
  int8_mask: true
dtype: float16

RichardErkhov/kyx0r_-_L3-Evil-Stheno-v3.2-8B-gguf