mergekit-community/mergekit-linear-enaoxvi

merge

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

Merge Details

Merge Method

This model was merged using the linear merge method.

Models Merged

The following models were included in the merge:

• ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.2
• DavidAU/L3.1-Dark-Planet-SpinFire-Uncensored-8B
• vicgalle/Humanish-Roleplay-Llama-3.1-8B

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: DavidAU/L3.1-Dark-Planet-SpinFire-Uncensored-8B
    parameters:
      weight: 0.55
  - model: ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.2
    parameters:
      weight: 0.3
  - model: vicgalle/Humanish-Roleplay-Llama-3.1-8B
    parameters:
      weight: 0.15
merge_method: linear  # You can change this based on the merge method you want to use
tokenizer_source: union  # Union tokenizer (adjust if necessary)
dtype: float16  # You can adjust dtype depending on your system