NeoSage-12B

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

Merge Details

Merge Method

This model was merged using the Task Arithmetic merge method using ../EsotericSage-12B-frank as a base.

Models Merged

The following models were included in the merge:

• ../Neona-12B

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: ../EsotericSage-12B-frank # good smarts & prose
    parameters:
      weight: 1.0
  - model: ../Neona-12B # decent coding & uncensor & roleplay
    parameters:
      weight: [0.25, 0.30, 0.75, 0.30, 0.25]
merge_method: task_arithmetic
base_model: ../EsotericSage-12B-frank # good smarts & prose
normalize: true
dtype: float16
chat_template: "chatml"
tokenizer:
  source: "base"