Resolving Interference When Merging Models
Paper • 2306.01708 • Published • 17
V2 of the MiraiFanfare with V3 of Blackroot and v0.1 of EVA.
This is a merge of pre-trained language models created using mergekit.
This model was merged using the TIES merge method using EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1 as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
models:
- model: Blackroot/Mirai-3.0-70B
parameters:
density: 0.4
weight: 0.35
- model: EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1
parameters:
density: 0.7
weight: 1
merge_method: ties
base_model: EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1
parameters:
normalize: true
dtype: bfloat16