I merged Steelskull/G2-DA-Nyxora-27b-V2 with nbeerbower/gemma2-gutenberg-27B using a 50/50 slerp merge.
Then I merged that with AALF/gemma-2-27b-it-SimPO-37K.
The model seems pretty decent at story telling in my limited testing.
base_model:
- AALF/gemma-2-27b-it-SimPO-37K
- DazzlingXeno/GutenBerg_Nyxora library_name: transformers tags:
- mergekit
- merge
merge
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the SLERP merge method.
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
base_model: AALF/gemma-2-27b-it-SimPO-37K
dtype: bfloat16
merge_method: slerp
parameters:
t:
- filter: self_attn
value: [0.0, 0.5, 0.3, 0.7, 1.0]
- filter: mlp
value: [1.0, 0.5, 0.7, 0.3, 0.0]
- value: 0.5
slices:
- sources:
- layer_range: [0, 46]
model: DazzlingXeno/GutenBerg_Nyxora
- layer_range: [0, 46]
model: AALF/gemma-2-27b-it-SimPO-37K
If you like it, but me a coffee https://ko-fi.com/dazzlingxeno