TareksLab/Anathema-V11-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 DARE TIES merge method using mlabonne/Hermes-3-Llama-3.1-70B-lorablated as a base.

Models Merged

The following models were included in the merge:

• SicariusSicariiStuff/Negative_LLAMA_70B
• Sao10K/L3-70B-Euryale-v2.1
• ReadyArt/Forgotten-Safeword-70B-v5.0
• 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: 0.30
      density: 0.5
  - model: mlabonne/Hermes-3-Llama-3.1-70B-lorablated
    parameters:
      weight: 0.25
      density: 0.5
  - model: Sao10K/L3-70B-Euryale-v2.1
    parameters:
      weight: 0.25
      density: 0.5
  - model: ReadyArt/Forgotten-Safeword-70B-v5.0
    parameters:
      weight: 0.10
      density: 0.5
  - model: SicariusSicariiStuff/Negative_LLAMA_70B 
    parameters:
      weight: 0.10
      density: 0.5
merge_method: dare_ties
base_model: mlabonne/Hermes-3-Llama-3.1-70B-lorablated
parameters:
  normalize: false
out_dtype: bfloat16
chat_template: llama3
tokenizer:
 source: mlabonne/Hermes-3-Llama-3.1-70B-lorablated