license: apache-2.0 | |
tags: | |
- merge | |
- mergekit | |
- lazymergekit | |
- nbeerbower/llama-3-spicy-abliterated-stella-8B | |
- Orenguteng/Llama-3-8B-Lexi-Uncensored | |
- aifeifei798/llama3-8B-DarkIdol-2.1-Uncensored-1048K | |
# Llama-3-instruct-Dare | |
Llama-3-instruct-Dare is a merge of the following models using [mergekit](https://github.com/cg123/mergekit): | |
* [nbeerbower/llama-3-spicy-abliterated-stella-8B](https://huggingface.co/nbeerbower/llama-3-spicy-abliterated-stella-8B) | |
* [Orenguteng/Llama-3-8B-Lexi-Uncensored](https://huggingface.co/Orenguteng/Llama-3-8B-Lexi-Uncensored) | |
* [aifeifei798/llama3-8B-DarkIdol-2.1-Uncensored-1048K](https://huggingface.co/aifeifei798/llama3-8B-DarkIdol-2.1-Uncensored-1048K) | |
## 🧩 Configuration | |
\```yaml | |
models: | |
- model: meta-llama/Meta-Llama-3-8B-Instruct | |
- model: nbeerbower/llama-3-spicy-abliterated-stella-8B | |
parameters: | |
density: 0.53 | |
weight: 0.3 | |
- model: Orenguteng/Llama-3-8B-Lexi-Uncensored | |
parameters: | |
density: 0.53 | |
weight: 0.4 | |
- model: aifeifei798/llama3-8B-DarkIdol-2.1-Uncensored-1048K | |
parameters: | |
density: 0.53 | |
weight: 0.3 | |
merge_method: dare_ties | |
base_model: meta-llama/Meta-Llama-3-8B-Instruct | |
parameters: | |
int8_mask: true | |
dtype: bfloat16 | |
\``` |