Modelpublic

mllm-dev/gpt2_m_experiment_ties

sourceHugging Faceupdated 2y agoView on Hugging Face

0likes7downloads

Model Card

seantestmerge_out

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

Merge Details

Merge Method

This model was merged using the TIES merge method using mllm-dev/gpt2_f_experiment_0 as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

yaml

base_model:
  model:
    path: mllm-dev/gpt2_f_experiment_0
dtype: float16
merge_method: ties
parameters:
  normalize: 1.0
slices:
- sources:
  - layer_range: [0, 12]
    model:
      model:
        path: mllm-dev/gpt2_f_experiment_0
  - layer_range: [0, 12]
    model:
      model:
        path: mllm-dev/gpt2_f_experiment_1
    parameters:
      density: 0.9
      weight: 0.1
  - layer_range: [0, 12]
    model:
      model:
        path: mllm-dev/gpt2_f_experiment_2
    parameters:
      density: 0.9
      weight: 0.1
  - layer_range: [0, 12]
    model:
      model:
        path: mllm-dev/gpt2_f_experiment_3
    parameters:
      density: 0.9
      weight: 0.1
  - layer_range: [0, 12]
    model:
      model:
        path: mllm-dev/gpt2_f_experiment_4
    parameters:
      density: 0.9
      weight: 0.1
  - layer_range: [0, 12]
    model:
      model:
        path: mllm-dev/gpt2_f_experiment_5
    parameters:
      density: 0.9
      weight: 0.1
  - layer_range: [0, 12]
    model:
      model:
        path: mllm-dev/gpt2_f_experiment_6
    parameters:
      density: 0.9
      weight: 0.1
  - layer_range: [0, 12]
    model:
      model:
        path: mllm-dev/gpt2_f_experiment_7
    parameters:
      density: 0.9
      weight: 0.1
  - layer_range: [0, 12]
    model:
      model:
        path: mllm-dev/gpt2_f_experiment_8
    parameters:
      density: 0.9
      weight: 0.1
  - layer_range: [0, 12]
    model:
      model:
        path: mllm-dev/gpt2_f_experiment_9
    parameters:
      density: 0.9
      weight: 0.1