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 unsloth/Llama-3.2-3B-Instruct as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
models:
- model: unsloth/Llama-3.2-3B-Instruct
# no parameters necessary for base model
- model: aabberick/Llama3.2-3b-H200-End_16bit
parameters:
density: 0.7
weight: 0.5
- model: aabberick/Llama3.2-3b-H200FamilyM
parameters:
density: 0.7
weight: 0.5
merge_method: ties
base_model: unsloth/Llama-3.2-3B-Instruct
parameters:
normalize: true
dtype: bfloat16