Cas-Warehouse/Llama-3-Mopeyfied-Psychology-8B

merge

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 Casual-Autopsy/Llama-3-Psychology-LoRA-Stock-8B as a base.

Models Merged

The following models were included in the merge:

• Casual-Autopsy/Llama-3-SOVL-MopeyMule-8B
• Casual-Autopsy/Llama-3-MopeyMule-Blackroot-8B

Configuration

The following YAML configuration was used to produce this model:

slices:
- sources:
  - model: Casual-Autopsy/Llama-3-Psychology-LoRA-Stock-8B
    layer_range: [0, 32]
    parameters:
      weight: 0.6
  - model: Casual-Autopsy/Llama-3-MopeyMule-Blackroot-8B
    layer_range: [0, 32]
    parameters:
      weight: 0.25
  - model: Casual-Autopsy/Llama-3-SOVL-MopeyMule-8B
    layer_range: [0, 32]
    parameters:
      weight: 0.15
merge_method: task_arithmetic
base_model: Casual-Autopsy/Llama-3-Psychology-LoRA-Stock-8B
normalize: False
dtype: bfloat16