olmoe-upscale-attempt1

output

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

Merge Details

Merge Method

This model was merged using the Passthrough merge method.

Models Merged

The following models were included in the merge:

• allenai/OLMoE-1B-7B-0125-Instruct

Configuration

The following YAML configuration was used to produce this model:

dtype: bfloat16
merge_method: passthrough
slices:
- sources:
  - layer_range: [0, 3]
    model: allenai/OLMoE-1B-7B-0125-Instruct
- sources:
  - layer_range: [4, 5]
    model: allenai/OLMoE-1B-7B-0125-Instruct
- sources:
  - layer_range: [4, 5]
    model: allenai/OLMoE-1B-7B-0125-Instruct
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0
- sources:
  - layer_range: [6, 7]
    model: allenai/OLMoE-1B-7B-0125-Instruct
- sources:
  - layer_range: [6, 7]
    model: allenai/OLMoE-1B-7B-0125-Instruct
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0
- sources:
  - layer_range: [8, 9]
    model: allenai/OLMoE-1B-7B-0125-Instruct
- sources:
  - layer_range: [8, 9]
    model: allenai/OLMoE-1B-7B-0125-Instruct
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0
- sources:
  - layer_range: [10, 11]
    model: allenai/OLMoE-1B-7B-0125-Instruct
- sources:
  - layer_range: [10, 11]
    model: allenai/OLMoE-1B-7B-0125-Instruct
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0
- sources:
  - layer_range: [12, 15]
    model: allenai/OLMoE-1B-7B-0125-Instruct