metadata
base_model:
- SicariusSicariiStuff/Dusk_Rainbow
- aifeifei798/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored
- Sao10K/Llama-3.1-8B-Stheno-v3.4
- akjindal53244/Llama-3.1-Storm-8B
library_name: transformers
tags:
- mergekit
- merge
BEFORE YOU USE THIS...
this is a merge [My first ever merge. Feedback is appreciated. Imo, it's decent?] This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the della_linear merge method using aifeifei798/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored as a base.
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
models:
- model: Sao10K/Llama-3.1-8B-Stheno-v3.4
parameters:
weight: 0.25
density: 0.84
- model: akjindal53244/Llama-3.1-Storm-8B
parameters:
weight: 0.4
density: 0.88
- model: SicariusSicariiStuff/Dusk_Rainbow
parameters:
weight: 0.6
density: 0.9
merge_method: della_linear
base_model: aifeifei798/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored
parameters:
int8_mask: true
epsilon: 0.07
lambda: 1
dtype: bfloat16