metadata
base_model:
- unsloth/Meta-Llama-3.1-8B-Instruct
- NCSOFT/Llama-VARCO-8B-Instruct
- Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2
- akjindal53244/Llama-3.1-Storm-8B
- arcee-ai/Llama-3.1-SuperNova-Lite
library_name: transformers
tags:
- mergekit
- merge
Untitled Model (1)
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 unsloth/Meta-Llama-3.1-8B-Instruct as a base.
Models Merged
The following models were included in the merge:
- NCSOFT/Llama-VARCO-8B-Instruct
- Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2
- akjindal53244/Llama-3.1-Storm-8B
- arcee-ai/Llama-3.1-SuperNova-Lite
Configuration
The following YAML configuration was used to produce this model:
base_model: unsloth/Meta-Llama-3.1-8B-Instruct
dtype: bfloat16
merge_method: dare_ties
slices:
- sources:
- layer_range: [0, 32]
model: akjindal53244/Llama-3.1-Storm-8B
parameters:
density: 0.8
weight: 0.13
- layer_range: [0, 32]
model: arcee-ai/Llama-3.1-SuperNova-Lite
parameters:
density: 1.0
weight: 0.37
- layer_range: [0, 32]
model: Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2
parameters:
density: 1.0
weight: 0.13
- layer_range: [0, 32]
model: NCSOFT/Llama-VARCO-8B-Instruct
parameters:
density: 0.8
weight: 0.37
- layer_range: [0, 32]
model: unsloth/Meta-Llama-3.1-8B-Instruct
tokenizer_source: base