TareksLab/Ruby-DT-V2-LLaMa-70B

MERGEDT

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/DarkThoughts-LLaMa-70B as a base.

Models Merged

The following models were included in the merge:

• TareksLab/DarkInstincts-LLaMa-70B
• TareksLab/DarkDesires-LLaMa-70B

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: TareksLab/DarkDesires-LLaMa-70B
    parameters:
      weight: 0.33
      density: 0.5
  - model: TareksLab/DarkInstincts-LLaMa-70B
    parameters:
      weight: 0.33
      density: 0.5
  - model: TareksLab/DarkThoughts-LLaMa-70B
    parameters:
      weight: 0.34
      density: 0.5
merge_method: dare_ties
base_model: TareksLab/DarkThoughts-LLaMa-70B
parameters:
  normalize: false
  int8_mask: true
dtype: float32
out_dtype: bfloat16
chat_template: llama3
tokenizer:
 source: union
 pad_to_multiple_of: 8