jaspionjader/bh-25

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/slu-37
• jaspionjader/bh-22

Configuration

The following YAML configuration was used to produce this model:

slices:
- sources:
  - model: jaspionjader/bh-22
    layer_range:
    - 0
    - 32
  - model: jaspionjader/slu-37
    layer_range:
    - 0
    - 32
merge_method: slerp
base_model: jaspionjader/bh-22
parameters:
  t:
  - filter: self_attn
    value:
    - 0.13
    - 0.09
    - 0.11
    - 0.12
    - 0.10
  - filter: mlp
    value:
    - 0.10
    - 0.12
    - 0.11
    - 0.09
    - 0.13
  - value: 0.11
dtype: bfloat16