Experimental RP merges - using SillyTavern with Min-P SanjiWatsuki/Loyal-Macaroni-Maid-7B, merged with ND911/EE-Maid-7B-Slerp which is a merge of SanjiWatsuki/Silicon-Maid-7B and maywell/Synatra-7B-v0.3-RP
EE-LMaid-7B-Slerp is a merge of the following models using LazyMergekit:
Franken-Maid-Slerp
Franken-Maid-Slerp is a merge of the following models using mergekit:
🧩 Configuration
slices:
- sources:
- model: SanjiWatsuki/Loyal-Toppy-Bruins-Maid-7B-DARE
layer_range: [0, 32]
- model: ND911/EE-LMaid-7B-Slerp
layer_range: [0, 32]
merge_method: slerp
base_model: ND911/EE-LMaid-7B-Slerp
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: bfloat16