metadata
base_model:
- TareksLab/DarkThoughts-V2-LLaMa-70B
- TareksLab/DarkInstincts-V2-LLaMa-70B
- huihui-ai/Llama-3.3-70B-Instruct-abliterated
- TareksLab/DarkDesires-V2-LLaMa-70B
library_name: transformers
tags:
- mergekit
- merge
MERGE2
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the DELLA merge method using huihui-ai/Llama-3.3-70B-Instruct-abliterated as a base.
Models Merged
The following models were included in the merge:
- TareksLab/DarkThoughts-V2-LLaMa-70B
- TareksLab/DarkInstincts-V2-LLaMa-70B
- TareksLab/DarkDesires-V2-LLaMa-70B
Configuration
The following YAML configuration was used to produce this model:
models:
- model: TareksLab/DarkDesires-V2-LLaMa-70B
parameters:
weight: [0.25, 0.30, 0.50]
density: 0.5
- model: TareksLab/DarkInstincts-V2-LLaMa-70B
parameters:
weight: [0.30, 0.45, 0.30]
density: 0.5
- model: TareksLab/DarkThoughts-V2-LLaMa-70B
parameters:
weight: [0.50, 0.30, 0.25]
density: 0.5
merge_method: della
base_model: huihui-ai/Llama-3.3-70B-Instruct-abliterated
parameters:
epsilon: 0.15
lambda: 1.1
normalize: false
dtype: float32
out_dtype: bfloat16
chat_template: llama3
tokenizer:
source: TareksLab/DarkThoughts-V2-LLaMa-70B
pad_to_multiple_of: 8