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 jpacifico/bitnet-dpo-merged-modelstock-retrain as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
models:
- model: jpacifico/bitnet-dpo-merged-modelstock-retrain
parameters:
density: 0.70
weight: 0.60
- model: jpacifico/bitnet-dpo-ties-retrained-mirror2
parameters:
density: 0.30
weight: 0.40
merge_method: ties
base_model: jpacifico/bitnet-dpo-merged-modelstock-retrain
parameters:
normalize: false
int8_mask: true
dtype: bfloat16