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 deepseek-ai/DeepSeek-R1-Distill-Llama-8B as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
models:
- model: deepseek-ai/DeepSeek-R1-Distill-Llama-8B
#no parameters necessary for base model
- model: avemio-digital/German-RAG-Mobius-DeepSeek-R1-ReDistill-LLAMA-8B-v1.1-SFT-DE
parameters:
density: 0.5
weight: 0.5
- model: mobiuslabsgmbh/DeepSeek-R1-ReDistill-Llama3-8B-v1.1
parameters:
density: 0.5
weight: 0.5
merge_method: dare_ties
base_model: deepseek-ai/DeepSeek-R1-Distill-Llama-8B
parameters:
normalize: false
int8_mask: true
dtype: float16