vulca2

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

Merge Details

Merge Method

This model was merged using the linear DARE merge method using merge/reshape as a base.

Models Merged

The following models were included in the merge:

merge/apollobulk

Configuration

The following YAML configuration was used to produce this model:

base_model: merge/reshape
dtype: bfloat16
merge_method: dare_linear
parameters:
  int8_mask: 1.0
  normalize: 0.0
slices:
- sources:
  - layer_range: [0, 32]
    model: merge/reshape
    parameters:
      weight: [0.1, 0.9]
  - layer_range: [0, 32]
    model: merge/apollobulk
    parameters:
      weight: [0.9, 0.1]
tokenizer_source: base