mergekit-community/LLaMa-3-Instruct-Zeroed-13B

merge

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

Merge Details

Merge Method

This model was merged using the passthrough merge method.

Models Merged

The following models were included in the merge:

• Undi95/Meta-Llama-3-8B-Instruct-hf

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
      - model: Undi95/Meta-Llama-3-8B-Instruct-hf
        layer_range: [0, 28]
  - sources:
      - model: Undi95/Meta-Llama-3-8B-Instruct-hf
        layer_range: [5, 28]
        parameters:
          scale:
            - filter: o_proj
              value: 0.0
            - filter: down_proj
              value: 0.0
            - value: 1.0
  - sources:
      - model: Undi95/Meta-Llama-3-8B-Instruct-hf
        layer_range: [28, 32]
merge_method: passthrough
dtype: bfloat16