jaspionjader/Kosmos-EVAA-Franken-Immersive-v40-8B

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:

• jaspionjader/Kosmos-EVAA-Franken-Immersive-v39-8B
• jaspionjader/knf-1-8b

Configuration

The following YAML configuration was used to produce this model:

slices:
- sources:
  - model: jaspionjader/Kosmos-EVAA-Franken-Immersive-v39-8B
    layer_range:
    - 0
    - 32
  - model: jaspionjader/knf-1-8b
    layer_range:
    - 0
    - 32
merge_method: slerp
base_model: jaspionjader/Kosmos-EVAA-Franken-Immersive-v39-8B
parameters:
  t:
  - filter: self_attn
    value:
    - 0.35
    - 0.25
    - 0.27
    - 0.33
    - 0.3
  - filter: mlp
    value:
    - 0.25
    - 0.35
    - 0.33
    - 0.27
    - 0.7
  - value: 0.41
dtype: bfloat16