Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch
Paper
β’ 2311.03099 β’ Published
β’ 30
This is a merge of pre-trained language models created using mergekit.
This model was merged using the DARE TIES merge method using MaziyarPanahi/Llama-3-8B-Instruct-v0.4 as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
models:
- model: MaziyarPanahi/Llama-3-8B-Instruct-v0.4
# No parameters necessary for base model
- model: netcat420/MFANNv0.17
parameters:
density: 0.53
weight: 0.5
- model: netcat420/MFANNv0.16
parameters:
density: 0.53
weight: 0.5
merge_method: dare_ties
base_model: MaziyarPanahi/Llama-3-8B-Instruct-v0.4
parameters:
int8_mask: true
dtype: bfloat16