mllm-dev/gpt2_m_experiment_dare_linear_1000

sean_test_merge_out

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 mllm-dev/gpt2_f_experiment_0_1000 as a base.

Models Merged

The following models were included in the merge:

• mllm-dev/gpt2_f_experiment_2_1000
• mllm-dev/gpt2_f_experiment_1_1000
• mllm-dev/gpt2_f_experiment_4_1000
• mllm-dev/gpt2_f_experiment_3_1000

Configuration

The following YAML configuration was used to produce this model:

base_model:
  model:
    path: mllm-dev/gpt2_f_experiment_0_1000
dtype: float16
merge_method: dare_ties
parameters:
  normalize: 1.0
slices:
- sources:
  - layer_range: [0, 12]
    model:
      model:
        path: mllm-dev/gpt2_f_experiment_0_1000
  - layer_range: [0, 12]
    model:
      model:
        path: mllm-dev/gpt2_f_experiment_1_1000
    parameters:
      density: 0.8
      weight: 0.3
  - layer_range: [0, 12]
    model:
      model:
        path: mllm-dev/gpt2_f_experiment_2_1000
    parameters:
      density: 0.6
      weight: 0.1
  - layer_range: [0, 12]
    model:
      model:
        path: mllm-dev/gpt2_f_experiment_3_1000
    parameters:
      density: 0.6
      weight: 0.1
  - layer_range: [0, 12]
    model:
      model:
        path: mllm-dev/gpt2_f_experiment_4_1000
    parameters:
      density: 0.8
      weight: 0.3