TareksGraveyard/Z-MODEL5-V1-DT

MERGE3

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/Doppleganger-V3-LLaMa-70B as a base.

Models Merged

The following models were included in the merge:

• Sao10K/L3.1-70B-Hanami-x1
• Mawdistical/Feral-Allura-70B
• Mawdistical/Vulpine-Seduction-70B

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: Mawdistical/Feral-Allura-70B
    parameters:
      weight: 0.25
      density: 0.5
  - model: Sao10K/L3.1-70B-Hanami-x1
    parameters:
      weight: 0.25
      density: 0.5
  - model: Mawdistical/Vulpine-Seduction-70B
    parameters:
      weight: 0.25
      density: 0.5
  - model: TareksLab/Doppleganger-V3-LLaMa-70B
    parameters:
      weight: 0.25
      density: 0.5
merge_method: dare_ties
base_model: TareksLab/Doppleganger-V3-LLaMa-70B
parameters:
  normalize: false
  int8_mask: true 
out_dtype: bfloat16
chat_template: llama3
tokenizer:
 source: union