metadata
base_model:
- Nohobby/YetAnotherMerge-v0.3
- MarinaraSpaghetti/NemoReRemix-12B
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 della merge method using MarinaraSpaghetti/NemoReRemix-12B as a base.
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
base_model: MarinaraSpaghetti/NemoReRemix-12B
parameters:
int8_mask: true
rescale: true
normalize: false
merge_method: della
dtype: bfloat16
models:
- model: Nohobby/YetAnotherMerge-v0.3
parameters:
density: [0.45, 0.55, 0.45, 0.55, 0.45]
epsilon: [0.1, 0.1, 0.25, 0.1, 0.1]
lambda: 0.85
weight: [0.55, 0.45, 0.55, 0.45, 0.55]