README.md

metadata

base_model:
  - UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3
  - ifable/gemma-2-Ifable-9B
  - nbeerbower/gemma2-gutenberg-9B
  - lemon07r/Gemma-2-Ataraxy-9B
library_name: transformers
tags:
  - mergekit
  - merge
license: other
language:
  - it
  - en

merge

This is a merge of pre-trained language models created using mergekit.

Merge Details

Excellent merge for writing texts and narratives Base Set dati Book Gutenberg

Merge Method

This model was merged using the DARE TIES merge method using nbeerbower/gemma2-gutenberg-9B as a base.

Models Merged

The following models were included in the merge:

• UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3
• ifable/gemma-2-Ifable-9B
• lemon07r/Gemma-2-Ataraxy-9B

Configuration

The following YAML configuration was used to produce this model:

merge_method: dare_ties
models:
  - model: nbeerbower/gemma2-gutenberg-9B
    parameters:
      weight: 0.25
  - model: UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3
    parameters:
      weight: 0.25
  - model: ifable/gemma-2-Ifable-9B
    parameters:
      weight: 0.25
  - model: lemon07r/Gemma-2-Ataraxy-9B
    parameters:
      weight: 0.25
base_model: nbeerbower/gemma2-gutenberg-9B
parameters:
  t: [0, 0.33, 0.67, 1]
dtype: bfloat16