Darkhn/Unhinged-RP-Alpha-V2-Llama-3.3-70B

merge

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 TareksLab/Wordsmith-V17-LLaMa-70B as a base.

Models Merged

The following models were included in the merge:

• Darkhn/Roleplay-Unhinged-Base-V2-Llama-3.3-70B
• Darkhn/Story-Unhinged-Base-V1-Llama-3.3-70B
• Darkhn/Negative-Unhinged-Base-V1-Llama-3.3-70B

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: Darkhn/Negative-Unhinged-Base-V1-Llama-3.3-70B
    parameters:
      weight: 0.25
      density: 0.7
  - model: Darkhn/Roleplay-Unhinged-Base-V2-Llama-3.3-70B
    parameters:
      weight: 0.25
      density: 0.5
  - model: Darkhn/Story-Unhinged-Base-V1-Llama-3.3-70B
    parameters:
      weight: 0.25
      density: 0.5
  - model: TareksLab/Wordsmith-V17-LLaMa-70B
    parameters:
      weight: 0.25
      density: 0.5
merge_method: dare_ties
base_model: TareksLab/Wordsmith-V17-LLaMa-70B
parameters:
  normalize: false
out_dtype: bfloat16
chat_template: llama3
tokenizer:
  source: base