dare

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

Merge Details

Merge Method

This model was merged using the DARE TIES merge method using cyberagent/calm2-7b-chat as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: cyberagent/calm2-7b-chat
    # No parameters necessary for base model
  - model: falche/opennovel_oc2_01a_7b
    parameters:
      density: 0.53
      weight: 0.5
  - model: offtoung/tsukuyomi-chan-calm2-7b
    parameters:
      density: 0.53
      weight: 0.5
merge_method: dare_ties
base_model: cyberagent/calm2-7b-chat
parameters:
  int8_mask: true
dtype: bfloat16