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 is a merge of the following models using
mergekit:
1slices:
2 - sources:
3 - model: SanjiWatsuki/Loyal-Toppy-Bruins-Maid-7B-DARE
4 layer_range: [0, 32]
5 - model: ND911/EE-LMaid-7B-Slerp
6 layer_range: [0, 32]
7merge_method: slerp
8base_model: ND911/EE-LMaid-7B-Slerp
9parameters:
10 t:
11 - filter: self_attn
12 value: [0, 0.5, 0.3, 0.7, 1]
13 - filter: mlp
14 value: [1, 0.5, 0.7, 0.3, 0]
15 - value: 0.5
16dtype: bfloat16
17
