Azazelle/L3-Decent-RP-8B

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:

• Azazelle/L3-Decent-Lois-Griffin-8B
• Azazelle/L3-Decent-Peter-Griffin-8B

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: Azazelle/L3-Decent-Peter-Griffin-8B
  - model: Azazelle/L3-Decent-Lois-Griffin-8B
merge_method: slerp
base_model: Azazelle/L3-Decent-Peter-Griffin-8B
parameters:
  t:
    - filter: self_attn
      value: [0.725, 0.725, 0.35, 0.35, 0.35, 0.35, 0.325, 0.325]
    - filter: mlp
      value: [0.775, 0.775, 0.4, 0.4, 0.4, 0.4, 0.375, 0.375]
    - value: [0.65, 0.4, 0.4, 0.35]
dtype: float16