Resolving Interference When Merging Models
Paper
•
2306.01708
•
Published
•
15
This is a merge of pre-trained language models created using mergekit.
This model was merged using the TIES merge method using /models/qwen3-4b-instruct-2507 as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
models:
- model: /models/game-top-ana4-4
parameters:
density: 0.5
weight: 1.0
- model: /models/print-top-0101928
parameters:
density: 0.5
weight: 1.0
- model: /models/lgc-v2-top-train11
parameters:
density: 0.5
weight: 1.0
merge_method: ties
base_model: /models/qwen3-4b-instruct-2507
parameters:
normalize: true
dtype: bfloat16