| license: apache-2.0 | |
| tags: | |
| - merge | |
| - mergekit | |
| - lazymergekit | |
| - vicgalle/Configurable-Llama-3.1-8B-Instruct | |
| - bunnycore/HyperLlama-3.1-8B | |
| - ValiantLabs/Llama3.1-8B-ShiningValiant2 | |
| # HyperLlama3.1-v2 | |
| HyperLlama3.1-v2 is a merge of the following models using [mergekit](https://github.com/cg123/mergekit): | |
| * [vicgalle/Configurable-Llama-3.1-8B-Instruct](https://huggingface.co/vicgalle/Configurable-Llama-3.1-8B-Instruct) | |
| * [bunnycore/HyperLlama-3.1-8B](https://huggingface.co/bunnycore/HyperLlama-3.1-8B) | |
| * [ValiantLabs/Llama3.1-8B-ShiningValiant2](https://huggingface.co/ValiantLabs/Llama3.1-8B-ShiningValiant2) | |
| ## 🧩 Configuration | |
| ```yaml | |
| slices: | |
| - sources: | |
| - model: vicgalle/Configurable-Llama-3.1-8B-Instruct | |
| parameters: | |
| weight: 1 | |
| layer_range: [0, 32] | |
| - model: bunnycore/HyperLlama-3.1-8B | |
| parameters: | |
| weight: 0.9 | |
| layer_range: [0, 32] | |
| - model: ValiantLabs/Llama3.1-8B-ShiningValiant2 | |
| parameters: | |
| weight: 0.6 | |
| layer_range: [0, 32] | |
| merge_method: task_arithmetic | |
| base_model: bunnycore/HyperLlama-3.1-8B | |
| parameters: | |
| t: | |
| - filter: self_attn | |
| value: [0, 0.5, 0.3, 0.7, 1] | |
| - filter: mlp | |
| value: [1, 0.5, 0.7, 0.3, 0] | |
| - value: 0.5 | |
| dtype: bfloat16 | |
| ``` |