R1-Broken-Tutu-24B

R1-Broken-Tutu-24B

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

Merge Details

Merge Method

This model was merged using the DARE TIES merge method using ReadyArt/The-Omega-Directive-M-24B-v1.1 as a base.

Models Merged

The following models were included in the merge:

• ReadyArt/Omega-Darker_The-Final-Directive-24B
• TheDrummer/Cydonia-R1-24B-v4
• ReadyArt/Forgotten-Safeword-24B
• TroyDoesAI/BlackSheep-24B

Configuration

The following YAML configuration was used to produce this model:

merge_method: dare_ties
base_model: ReadyArt/The-Omega-Directive-M-24B-v1.1
models:
  - model: ReadyArt/The-Omega-Directive-M-24B-v1.1
    parameters:
      weight: 0.2
  - model: ReadyArt/Omega-Darker_The-Final-Directive-24B
    parameters:
      weight: 0.2
  - model: ReadyArt/Forgotten-Safeword-24B
    parameters:
      weight: 0.2
  - model: TroyDoesAI/BlackSheep-24B
    parameters:
      weight: 0.2
  - model: TheDrummer/Cydonia-R1-24B-v4
    parameters:
      weight: 0.2
parameters:
  density: 0.3
tokenizer:
  source: union
chat_template: auto

Special thanks

• TheDrummer (Cydonia Model Architect)
• TroyDoesAI (BlackSheep Architect)
• SteelSkull (Dataset Generation Contributor)
• sleepdeprived3 (Omega / Safeword)