Resolving Interference When Merging Models
Paper
•
2306.01708
•
Published
•
15
This is a merge of pre-trained language models created using mergekitty.
This model was merged using the TIES merge method using Qwen/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-Marigold-v0-exp
parameters:
weight: 1
density: 1
- model: trashpanda-org/Qwen2.5-32B-Marigold-v0
parameters:
weight: 1
density: 1
- model: huihui-ai/QwQ-32B-abliterated
parameters:
weight: 0.9
density: 0.9
merge_method: ties
base_model: Qwen/Qwen2.5-32B
parameters:
weight: 0.9
density: 0.9
normalize: true
int8_mask: true
tokenizer:
source: "base"
pad_to_multiple_of: 152064
dtype: bfloat16