Azazelle/Llama-3-8B-contaminated-roleplay

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 ResplendentAI/Aura_Uncensored_l3_8B as a base.

Models Merged

The following models were included in the merge:

• vicgalle/Roleplay-Llama-3-8B
• Undi95/Llama-3-LewdPlay-8B-evo
• abhishek/autotrain-llama3-orpo

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: ResplendentAI/Aura_Uncensored_l3_8B
  - model: abhishek/autotrain-llama3-orpo
  - model: vicgalle/Roleplay-Llama-3-8B
  - model: Undi95/Llama-3-LewdPlay-8B-evo
merge_method: model_stock
base_model: ResplendentAI/Aura_Uncensored_l3_8B
dtype: bfloat16