yuiseki/YuisekinAIEvol-Mistral-7B-ja-math-v0.1.1

tmp

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

Merge Details

Merge Method

This model was merged using the task arithmetic merge method using ./evol_merge_storage/input_models/Mistral-7B-Instruct-v0.2_674785087 as a base.

Models Merged

The following models were included in the merge:

• ./evol_merge_storage/input_models/OpenMath-Mistral-7B-v0.1-hf_3930120330
• ./evol_merge_storage/input_models/RakutenAI-7B-chat_2028928689

Configuration

The following YAML configuration was used to produce this model:

base_model: ./evol_merge_storage/input_models/Mistral-7B-Instruct-v0.2_674785087
dtype: bfloat16
merge_method: task_arithmetic
parameters:
  int8_mask: 1.0
  normalize: 0.0
slices:
- sources:
  - layer_range: [0, 4]
    model: ./evol_merge_storage/input_models/RakutenAI-7B-chat_2028928689
    parameters:
      weight: 0.7279377399402179
  - layer_range: [0, 4]
    model: ./evol_merge_storage/input_models/OpenMath-Mistral-7B-v0.1-hf_3930120330
    parameters:
      weight: 0.15295380041554363
  - layer_range: [0, 4]
    model: ./evol_merge_storage/input_models/Mistral-7B-Instruct-v0.2_674785087
    parameters:
      weight: -0.08929832001917964
- sources:
  - layer_range: [4, 8]
    model: ./evol_merge_storage/input_models/RakutenAI-7B-chat_2028928689
    parameters:
      weight: 0.691881657249384
  - layer_range: [4, 8]
    model: ./evol_merge_storage/input_models/OpenMath-Mistral-7B-v0.1-hf_3930120330
    parameters:
      weight: 0.2922325727237859
  - layer_range: [4, 8]
    model: ./evol_merge_storage/input_models/Mistral-7B-Instruct-v0.2_674785087
    parameters:
      weight: 0.5080572203176679
- sources:
  - layer_range: [8, 12]
    model: ./evol_merge_storage/input_models/RakutenAI-7B-chat_2028928689
    parameters:
      weight: 0.09187783621015794
  - layer_range: [8, 12]
    model: ./evol_merge_storage/input_models/OpenMath-Mistral-7B-v0.1-hf_3930120330
    parameters:
      weight: -0.012485482975296447
  - layer_range: [8, 12]
    model: ./evol_merge_storage/input_models/Mistral-7B-Instruct-v0.2_674785087
    parameters:
      weight: 0.41795960652363595
- sources:
  - layer_range: [12, 16]
    model: ./evol_merge_storage/input_models/RakutenAI-7B-chat_2028928689
    parameters:
      weight: 0.34681087119307275
  - layer_range: [12, 16]
    model: ./evol_merge_storage/input_models/OpenMath-Mistral-7B-v0.1-hf_3930120330
    parameters:
      weight: -0.06403292076991726
  - layer_range: [12, 16]
    model: ./evol_merge_storage/input_models/Mistral-7B-Instruct-v0.2_674785087
    parameters:
      weight: 0.09721311625574781
- sources:
  - layer_range: [16, 20]
    model: ./evol_merge_storage/input_models/RakutenAI-7B-chat_2028928689
    parameters:
      weight: 0.5121357281800163
  - layer_range: [16, 20]
    model: ./evol_merge_storage/input_models/OpenMath-Mistral-7B-v0.1-hf_3930120330
    parameters:
      weight: 0.6220102021390902
  - layer_range: [16, 20]
    model: ./evol_merge_storage/input_models/Mistral-7B-Instruct-v0.2_674785087
    parameters:
      weight: 0.18620926164035395
- sources:
  - layer_range: [20, 24]
    model: ./evol_merge_storage/input_models/RakutenAI-7B-chat_2028928689
    parameters:
      weight: 0.41782286184995043
  - layer_range: [20, 24]
    model: ./evol_merge_storage/input_models/OpenMath-Mistral-7B-v0.1-hf_3930120330
    parameters:
      weight: 0.4421406594473506
  - layer_range: [20, 24]
    model: ./evol_merge_storage/input_models/Mistral-7B-Instruct-v0.2_674785087
    parameters:
      weight: 0.17389465072652804
- sources:
  - layer_range: [24, 28]
    model: ./evol_merge_storage/input_models/RakutenAI-7B-chat_2028928689
    parameters:
      weight: 0.49147162824520074
  - layer_range: [24, 28]
    model: ./evol_merge_storage/input_models/OpenMath-Mistral-7B-v0.1-hf_3930120330
    parameters:
      weight: 0.33754092637416533
  - layer_range: [24, 28]
    model: ./evol_merge_storage/input_models/Mistral-7B-Instruct-v0.2_674785087
    parameters:
      weight: 0.44509618118199307
- sources:
  - layer_range: [28, 32]
    model: ./evol_merge_storage/input_models/RakutenAI-7B-chat_2028928689
    parameters:
      weight: 0.35777289734770956
  - layer_range: [28, 32]
    model: ./evol_merge_storage/input_models/OpenMath-Mistral-7B-v0.1-hf_3930120330
    parameters:
      weight: 0.18435978508773565
  - layer_range: [28, 32]
    model: ./evol_merge_storage/input_models/Mistral-7B-Instruct-v0.2_674785087
    parameters:
      weight: 0.3646502716264272