---
license: apache-2.0
tags:
- merge
- mergekit
- lazymergekit
- stephenlzc/dolphin-llama3-zh-cn-uncensored
- georgesung/llama3_8b_chat_uncensored
- aifeifei798/llama3-8B-DarkIdol-2.1-Uncensored-32K
---

# Testing

Testing is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
* [stephenlzc/dolphin-llama3-zh-cn-uncensored](https://huggingface.co/stephenlzc/dolphin-llama3-zh-cn-uncensored)
* [georgesung/llama3_8b_chat_uncensored](https://huggingface.co/georgesung/llama3_8b_chat_uncensored)
* [aifeifei798/llama3-8B-DarkIdol-2.1-Uncensored-32K](https://huggingface.co/aifeifei798/llama3-8B-DarkIdol-2.1-Uncensored-32K)

## 🧩 Configuration

\```yaml
models:
  - model: Orenguteng/Llama-3-8B-Lexi-Uncensored
  - model: stephenlzc/dolphin-llama3-zh-cn-uncensored
    parameters:
      density: 0.53
      weight: 0.4
  - model: georgesung/llama3_8b_chat_uncensored
    parameters:
      density: 0.53
      weight: 0.3
  - model: aifeifei798/llama3-8B-DarkIdol-2.1-Uncensored-32K
    parameters:
      density: 0.53
      weight: 0.3
merge_method: dare_ties
base_model: Orenguteng/Llama-3-8B-Lexi-Uncensored
parameters:
  int8_mask: true
dtype: bfloat16
\```