Swallow-MS-7b-MergeEvol-fevals105-norm

final_merge

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 ../evol_merge_storage/input_models/Swallow-MS-7b-v0.1_259979065 as a base.

Models Merged

The following models were included in the merge:

• ../evol_merge_storage/input_models/Mistral-7B-Instruct-v0.2_674785087
• ../evol_merge_storage/input_models/Starling-LM-7B-beta_581094980

Configuration

The following YAML configuration was used to produce this model:

base_model: ../evol_merge_storage/input_models/Swallow-MS-7b-v0.1_259979065
dtype: bfloat16
merge_method: dare_ties
parameters:
  int8_mask: 1.0
  normalize: 1.0
slices:
- sources:
  - layer_range: [0, 4]
    model: ../evol_merge_storage/input_models/Swallow-MS-7b-v0.1_259979065
    parameters:
      density: 0.6849374987082797
      weight: 0.41688291356235085
  - layer_range: [0, 4]
    model: ../evol_merge_storage/input_models/Starling-LM-7B-beta_581094980
    parameters:
      density: 1.0
      weight: 0.22402138180057965
  - layer_range: [0, 4]
    model: ../evol_merge_storage/input_models/Mistral-7B-Instruct-v0.2_674785087
    parameters:
      density: 1.0
      weight: 0.14273100451544973
- sources:
  - layer_range: [4, 8]
    model: ../evol_merge_storage/input_models/Swallow-MS-7b-v0.1_259979065
    parameters:
      density: 1.0
      weight: 0.27745773580979954
  - layer_range: [4, 8]
    model: ../evol_merge_storage/input_models/Starling-LM-7B-beta_581094980
    parameters:
      density: 0.8641797141160683
      weight: 0.21900101081627826
  - layer_range: [4, 8]
    model: ../evol_merge_storage/input_models/Mistral-7B-Instruct-v0.2_674785087
    parameters:
      density: 0.7045066746748807
      weight: 0.27219079838557547
- sources:
  - layer_range: [8, 12]
    model: ../evol_merge_storage/input_models/Swallow-MS-7b-v0.1_259979065
    parameters:
      density: 0.9344897829414548
      weight: 0.39771623371112386
  - layer_range: [8, 12]
    model: ../evol_merge_storage/input_models/Starling-LM-7B-beta_581094980
    parameters:
      density: 1.0
      weight: 0.5638393619932354
  - layer_range: [8, 12]
    model: ../evol_merge_storage/input_models/Mistral-7B-Instruct-v0.2_674785087
    parameters:
      density: 1.0
      weight: 0.45491072302164476
- sources:
  - layer_range: [12, 16]
    model: ../evol_merge_storage/input_models/Swallow-MS-7b-v0.1_259979065
    parameters:
      density: 1.0
      weight: 0.043782836287435234
  - layer_range: [12, 16]
    model: ../evol_merge_storage/input_models/Starling-LM-7B-beta_581094980
    parameters:
      density: 1.0
      weight: 0.12905392091616227
  - layer_range: [12, 16]
    model: ../evol_merge_storage/input_models/Mistral-7B-Instruct-v0.2_674785087
    parameters:
      density: 1.0
      weight: 0.32911680921058395
- sources:
  - layer_range: [16, 20]
    model: ../evol_merge_storage/input_models/Swallow-MS-7b-v0.1_259979065
    parameters:
      density: 1.0
      weight: 0.33223757646195995
  - layer_range: [16, 20]
    model: ../evol_merge_storage/input_models/Starling-LM-7B-beta_581094980
    parameters:
      density: 1.0
      weight: 0.21148775085590665
  - layer_range: [16, 20]
    model: ../evol_merge_storage/input_models/Mistral-7B-Instruct-v0.2_674785087
    parameters:
      density: 1.0
      weight: 0.3100840123708662
- sources:
  - layer_range: [20, 24]
    model: ../evol_merge_storage/input_models/Swallow-MS-7b-v0.1_259979065
    parameters:
      density: 1.0
      weight: 0.047668810469104206
  - layer_range: [20, 24]
    model: ../evol_merge_storage/input_models/Starling-LM-7B-beta_581094980
    parameters:
      density: 1.0
      weight: 0.38364985576700883
  - layer_range: [20, 24]
    model: ../evol_merge_storage/input_models/Mistral-7B-Instruct-v0.2_674785087
    parameters:
      density: 1.0
      weight: 0.7458689345554008
- sources:
  - layer_range: [24, 28]
    model: ../evol_merge_storage/input_models/Swallow-MS-7b-v0.1_259979065
    parameters:
      density: 1.0
      weight: 0.6585871690360476
  - layer_range: [24, 28]
    model: ../evol_merge_storage/input_models/Starling-LM-7B-beta_581094980
    parameters:
      density: 1.0
      weight: 0.11141636691846393
  - layer_range: [24, 28]
    model: ../evol_merge_storage/input_models/Mistral-7B-Instruct-v0.2_674785087
    parameters:
      density: 1.0
      weight: 0.6680264219734943
- sources:
  - layer_range: [28, 32]
    model: ../evol_merge_storage/input_models/Swallow-MS-7b-v0.1_259979065
    parameters:
      density: 1.0
      weight: 0.554815190090898
  - layer_range: [28, 32]
    model: ../evol_merge_storage/input_models/Starling-LM-7B-beta_581094980
    parameters:
      density: 1.0
      weight: 0.38561479058158477
  - layer_range: [28, 32]
    model: ../evol_merge_storage/input_models/Mistral-7B-Instruct-v0.2_674785087
    parameters:
      density: 0.9671800407644409
      weight: 0.16533929845269846
tokenizer_source: base