Llama-3.1-8b-Uncensored-Dare

Llama-3.1-8b-Uncensored-Dare is a merge of the following models using mergekit:

• aifeifei798/DarkIdol-Llama-3.1-8B-Instruct-1.0-Uncensored
• aifeifei798/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored
• Orenguteng/Llama-3-8B-Lexi-Uncensored
• aifeifei798/DarkIdol-Llama-3.1-8B-Instruct-1.1-Uncensored

🧩 Configuration

```yaml models:

• model: Orenguteng/Llama-3.1-8B-Lexi-Uncensored
• model: aifeifei798/DarkIdol-Llama-3.1-8B-Instruct-1.0-Uncensored parameters: density: 0.53 weight: 0.4
• model: aifeifei798/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored parameters: density: 0.53 weight: 0.3
• model: Orenguteng/Llama-3-8B-Lexi-Uncensored parameters: density: 0.53 weight: 0.2
• model: aifeifei798/DarkIdol-Llama-3.1-8B-Instruct-1.1-Uncensored parameters: density: 0.53 weight: 0.1 merge_method: dare_ties base_model: Orenguteng/Llama-3.1-8B-Lexi-Uncensored parameters: int8_mask: true dtype: bfloat16 ```