Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch
Paper • 2311.03099 • Published • 32
This is a merge of pre-trained language models created using mergekit.
This model was merged using the DARE TIES merge method using google/gemma-3-1b-pt as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
models:
- model: swarup3204/gemma-3-1b-pt-ft
parameters:
weight: 1.0
density: 0.66
merge_method: dare_ties
base_model: google/gemma-3-1b-pt
dtype: bfloat16
parameters:
normalize: false
int8_mask: true