metadata
base_model:
- Undi95/Llama-3-LewdPlay-8B-evo
- NousResearch/Hermes-2-Pro-Llama-3-8B
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 DARE TIES merge method using Undi95/Llama-3-LewdPlay-8B-evo 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: Undi95/Llama-3-LewdPlay-8B-evo
# No parameters necessary for base model
- model: NousResearch/Hermes-2-Pro-Llama-3-8B
parameters:
density: 0.53
weight: 0.4
merge_method: dare_ties
base_model: Undi95/Llama-3-LewdPlay-8B-evo
parameters:
int8_mask: true
dtype: bfloat16