DopeyGay/L3-Unholy-Mind-RP-v0.1

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 Undi95/Llama-3-Unholy-8B as a base.

Models Merged

The following models were included in the merge:

• Dampfinchen/Llama-3-8B-Ultra-Instruct
• R136a1/Bungo-L3-8B
• SicariusSicariiStuff/Dusk_Rainbow
• Casual-Autopsy/L3-Umbral-Mind-RP-v3.0-8B

Configuration

The following YAML configuration was used to produce this model:

slices:
- sources:
  - model: Undi95/Llama-3-Unholy-8B
    layer_range: [0, 32]
    parameters:
      weight: 0.55
  - model: Casual-Autopsy/L3-Umbral-Mind-RP-v3.0-8B
    layer_range: [0, 32]
    parameters:
      weight: 0.5
  - model: SicariusSicariiStuff/Dusk_Rainbow
    layer_range: [0, 32]
    parameters:
      weight: 0.25
  - model: Dampfinchen/Llama-3-8B-Ultra-Instruct
    layer_range: [0, 32]
    parameters:
      weight: 0.15
  - model: R136a1/Bungo-L3-8B
    layer_range: [0, 32]
    parameters:
      weight: 0.1
merge_method: task_arithmetic
base_model: Undi95/Llama-3-Unholy-8B
normalize: False
dtype: bfloat16