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 Qwen/Qwen2.5-3B as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
merge_method: dare_ties
base_model: Qwen/Qwen2.5-3B
models:
- model: Qwen/Qwen2.5-3B
parameters:
density: 0.5
weight: 0.4
- model: Qwen/Qwen2.5-Coder-3B
parameters:
density: 0.4
weight: 0.35
dtype: float16
out_path: ./merged-qwen-dare