narpas/UNNAMED-MODEL-D-4.0bpw-h8-exl2

MERGE4

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

Merge Details

Merge Method

This model was merged using the DELLA merge method using TareksLab/Scrivener-Base-V4-LLaMA-70B as a base.

Models Merged

The following models were included in the merge:

• TareksLab/Anathema-V2-LLaMA-70B
• TareksLab/Erudite-V1-Unleashed-LLaMA-70B
• TareksLab/RolePlayer-V4-LLaMa-70B
• TareksLab/Wordsmith-V2.0-LLaMa-70B

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: TareksLab/Wordsmith-V2.0-LLaMa-70B
    parameters:
      weight: 0.20
      density: 0.5
      epsilon: 0.05
      lambda: 1.0
  - model: TareksLab/Anathema-V2-LLaMA-70B
    parameters:
      weight: 0.20
      density: 0.5
      epsilon: 0.05
      lambda: 1.0
  - model: TareksLab/Scrivener-Base-V4-LLaMA-70B
    parameters:
      weight: 0.20
      density: 0.5
      epsilon: 0.05
      lambda: 1.0
  - model: TareksLab/RolePlayer-V4-LLaMa-70B
    parameters:
      weight: 0.20
      density: 0.5
      epsilon: 0.05
      lambda: 1.0
  - model: TareksLab/Erudite-V1-Unleashed-LLaMA-70B
    parameters:
      weight: 0.20
      density: 0.5
      epsilon: 0.05
      lambda: 1.0
merge_method: della
base_model: TareksLab/Scrivener-Base-V4-LLaMA-70B
parameters:
  normalize: false
  int8_mask: true
dtype: bfloat16
chat_template: llama3
tokenizer:
 source: TareksLab/Scrivener-Base-V4-LLaMA-70B