metadata
base_model:
- TheDrummer/Fallen-Llama-3.3-R1-70B-v1
- ReadyArt/Fallen-Safeword-70B-R1-v4.1
- ReadyArt/Forgotten-Safeword-70B-3.6
- ReadyArt/Fallen-Abomination-70B-R1-v4.1
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 Linear DELLA merge method using ReadyArt/Forgotten-Safeword-70B-3.6 as a base.
Models Merged
The following models were included in the merge:
- TheDrummer/Fallen-Llama-3.3-R1-70B-v1
- ReadyArt/Fallen-Safeword-70B-R1-v4.1
- ReadyArt/Fallen-Abomination-70B-R1-v4.1
Configuration
The following YAML configuration was used to produce this model:
models:
- model: TheDrummer/Fallen-Llama-3.3-R1-70B-v1
parameters:
weight: 0.25
density: 0.7
epsilon: 0.2
lambda: 1.1
- model: ReadyArt/Fallen-Abomination-70B-R1-v4.1
parameters:
weight: 0.25
density: 0.7
epsilon: 0.2
lambda: 1.1
- model: ReadyArt/Fallen-Safeword-70B-R1-v4.1
parameters:
weight: 0.25
density: 0.7
epsilon: 0.2
lambda: 1.1
- model: ReadyArt/Forgotten-Safeword-70B-3.6
parameters:
weight: 0.25
density: 0.7
epsilon: 0.1
lambda: 1.0
base_model: ReadyArt/Forgotten-Safeword-70B-3.6
merge_method: della_linear
parameters:
normalize: false
tokenizer:
source: base
dtype: bfloat16
chat_template: llama3