metadata
base_model:
- NeverSleep/Lumimaid-v0.2-8B
- vicgalle/Roleplay-Hermes-3-Llama-3.1-8B
- ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.2
- aifeifei798/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored
- OddTheGreat/Rrat_8B_v.2
library_name: transformers
tags:
- mergekit
- merge
merge
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the TIES merge method using OddTheGreat/Rrat_8B_v.2 as a base.
Models Merged
The following models were included in the merge:
- NeverSleep/Lumimaid-v0.2-8B
- vicgalle/Roleplay-Hermes-3-Llama-3.1-8B
- ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.2
- aifeifei798/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored
Configuration
The following YAML configuration was used to produce this model:
models:
- model: OddTheGreat/Rrat_8B_v.2
parameters:
density: 0.9
weight: 0.9
- model: aifeifei798/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored
parameters:
density: 0.3
weight: 0.3
- model: ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.2
parameters:
density: 0.3
weight: 0.3
- model: NeverSleep/Lumimaid-v0.2-8B
parameters:
density: 0.3
weight: 0.3
- model: vicgalle/Roleplay-Hermes-3-Llama-3.1-8B
parameters:
density: 0.3
weight: 0.3
merge_method: ties
base_model: OddTheGreat/Rrat_8B_v.2
parameters:
normalize: false
int8_mask: true
dtype: float16
tokenizer:
source: union