Darkhn/Roleplay-Abliterated-Base-V3-Llama-3.3-70B

merge

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

Merge Details

Merge Method

This model was merged using the Model Stock merge method using huihui-ai/Llama-3.3-70B-Instruct-abliterated as a base.

Models Merged

The following models were included in the merge:

• EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1
• Sao10K/70B-L3.3-Cirrus-x1
• Sao10K/L3.3-70B-Euryale-v2.3
• SicariusSicariiStuff/Negative_LLAMA_70B

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: Sao10K/70B-L3.3-Cirrus-x1
    parameters:
      weight: 0.2
      density: 0.8
  - model: Sao10K/L3.3-70B-Euryale-v2.3
    parameters:
      weight: 0.2
      density: 0.8
  - model: EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1
    parameters:
      weight: 0.2
      density: 0.6
  - model: SicariusSicariiStuff/Negative_LLAMA_70B
    parameters:
      weight: 0.20
      density: 0.6
  - model: huihui-ai/Llama-3.3-70B-Instruct-abliterated
    parameters:
      weight: 0.2
      density: 0.4
merge_method: model_stock
base_model: huihui-ai/Llama-3.3-70B-Instruct-abliterated
parameters:
  normalize: false
  int8_mask: true
dtype: float16
out_dtype: bfloat16
chat_template: llama3
tokenizer:
  source: base