Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch
Paper
•
2311.03099
•
Published
•
30
This is a merge of pre-trained language models created using mergekit.
This model was merged using the DARE TIES merge method using Blazgo/2-pro-base as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
models:
- model: Blazgo/2-pro-base
- model: ricdomolm/lawma-70b
parameters:
density: 0.8
weight: 0.8
merge_method: dare_ties
base_model: Blazgo/2-pro-base
parameters:
normalize: false
int8_mask: true
dtype: float16