Working Merge in my Profile
Collection
25 items
•
Updated
•
1
This is a merge of pre-trained language models created using mergekit.
This model was merged using the SLERP merge method.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
models:
- model: zelk12/MT-Merge2-MU-gemma-2-MTg2MT1g2-9B
- model: allknowingroger/GemmaSlerp5-10B
merge_method: slerp
base_model: allknowingroger/GemmaSlerp5-10B
dtype: float32
out_dtype: bfloat16
parameters:
t: [0.41,0.39,0.37,0.34,0.3,0.26,0.43,0.63,0.66,0.69,0.72,0.77,0.84,0.91,1]