SCETest4-70B

merge

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

Merge Details

Merge Method

This model was merged using the SCE merge method using SicariusSicariiStuff/Negative_LLAMA_70B as a base.

Models Merged

The following models were included in the merge:

• ReadyArt/Forgotten-Safeword-70B-v5.0
• LatitudeGames/Wayfarer-Large-70B-Llama-3.3
• allura-org/Bigger-Body-70b
• TheDrummer/Fallen-Llama-3.3-R1-70B-v1

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: TheDrummer/Fallen-Llama-3.3-R1-70B-v1
    parameters:
      weight: 0.20
      density: 0.8
      select_topk: 0.15
      lambda: 1.0
  - model: ReadyArt/Forgotten-Safeword-70B-v5.0
    parameters:
      weight: 0.20
      density: 0.8
      select_topk: 0.15
      lambda: 1.0
  - model: allura-org/Bigger-Body-70b
    parameters:
      weight: 0.20
      density: 0.8
      select_topk: 0.15
      lambda: 1.0
  - model: LatitudeGames/Wayfarer-Large-70B-Llama-3.3
    parameters:
      weight: 0.20
      density: 0.8
      select_topk: 0.15
      lambda: 1.0
  - model: SicariusSicariiStuff/Negative_LLAMA_70B
    parameters:
      weight: 0.20
      density: 0.8
      select_topk: 0.15
      lambda: 1.0
base_model: SicariusSicariiStuff/Negative_LLAMA_70B
merge_method: sce
parameters:
  normalize: false
  int8_mask: true
tokenizer:
  source: SicariusSicariiStuff/Negative_LLAMA_70B
chat_template: llama3
dtype: bfloat16