TareksLab/Anathema-V8-LLaMA-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 huihui-ai/Llama-3.3-70B-Instruct-abliterated as a base.

Models Merged

The following models were included in the merge:

• TheDrummer/Fallen-Llama-3.3-R1-70B-v1
• ReadyArt/Fallen-Abomination-70B-R1-v4.1
• Sao10K/L3-70B-Euryale-v2.1
• ReadyArt/Fallen-Safeword-70B-R1-v4.1
• mlabonne/Hermes-3-Llama-3.1-70B-lorablated

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: TheDrummer/Fallen-Llama-3.3-R1-70B-v1
    parameters:
       select_topk: 0.20
  - model: ReadyArt/Fallen-Safeword-70B-R1-v4.1
    parameters:
       select_topk: 0.10
  - model: ReadyArt/Fallen-Abomination-70B-R1-v4.1
    parameters:
       select_topk: 0.10
  - model: mlabonne/Hermes-3-Llama-3.1-70B-lorablated
    parameters:
       select_topk: 0.20
  - model: Sao10K/L3-70B-Euryale-v2.1
    parameters:
       select_topk: 0.20
merge_method: sce
base_model: huihui-ai/Llama-3.3-70B-Instruct-abliterated
dtype: bfloat16
tokenizer:
 source: base