Resolving Interference When Merging Models
Paper
•
2306.01708
•
Published
•
16
This is a merge of pre-trained language models created using mergekit.
This model was merged using the TIES merge method using natong19/Mistral-Nemo-Instruct-2407-abliterated as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
merge_method: ties
dtype: bfloat16
out_dtype: bfloat16
base_model: natong19/Mistral-Nemo-Instruct-2407-abliterated
models:
- model: Elizezen/Himeyuri-v0.1-12B
parameters:
density: 0.75
weight: 0.8
- model: shisa-ai/shisa-v2-mistral-nemo-12b
parameters:
density: 0.6
weight: 0.6