Darkhn/Alkahest-V4-Unhinged-RP-Alpha-V1-Llama-3.3-70B-Fail

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 TareksTesting/Alkahest-V4-LLaMa-70B as a base.

Models Merged

The following models were included in the merge:

• Darkhn/Unhinged-RP-Alpha-V1-Llama-3.3-70B

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: TareksTesting/Alkahest-V4-LLaMa-70B
    parameters:
      density: 0.75
      weight: 0.75
  - model: Darkhn/Unhinged-RP-Alpha-V1-Llama-3.3-70B
    parameters:
      density: 0.3
      weight: 0.3
merge_method: dare_ties
base_model: TareksTesting/Alkahest-V4-LLaMa-70B
parameters:
  normalize: false
  int8_mask: true
dtype: bfloat16
chat_template: llama3
tokenizer:
 source: base