tensorwa/dp_mg_h01

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:

• itorgov/model-1738289983
• Peacoc/chatml_2test43

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
      - model: itorgov/model-1738289983
        layer_range: [0, 32]
      - model: Peacoc/chatml_2test43
        layer_range: [0, 32]
merge_method: slerp
base_model: itorgov/model-1738289983
parameters:
  t:
    - filter: self_attn
      value: 0.99
    - filter: mlp
      value: 0.98
    - value: 1
dtype: bfloat16