Resolving Interference When Merging Models
Paper • 2306.01708 • Published • 18
This is a merge of pre-trained language models created using mergekit.
This model was merged using the TIES merge method using Columbidae/Qwen2.5-32B as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
models:
- model: trashpanda-org/Qwen2.5-32B-Dark-Days-stage1
parameters:
weight: 1
density: 1
- model: trashpanda-org/Qwen2.5-32B-Dark-Days-stage2
parameters:
weight: 1
density: 1
- model: Columbidae/Qwen2.5-32B-Instruct
parameters:
weight: 0.9
density: 0.9
merge_method: ties
base_model: Columbidae/Qwen2.5-32B
parameters:
weight: 0.9
density: 0.9
normalize: true
int8_mask: true
tokenizer_source: Columbidae/Qwen2.5-32B-Instruct
dtype: bfloat16