README.md

metadata

base_model:
  - TheDrummer/Gemmasutra-Pro-27B-v1
  - nbeerbower/gemma2-gutenberg-27B
  - AALF/gemma-2-27b-it-SimPO-37K
tags:
  - Story Telling
  - Creative Writing
  - GutenBerg
  - Gemma
  - Prose

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:

• AALF/gemma-2-27b-it-SimPO-37K
• DazzlingXeno/GutenBerg_Nyxora

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