| license: apache-2.0 | |
| tags: | |
| - merge | |
| - mergekit | |
| - lazymergekit | |
| - gordicaleksa/YugoGPT | |
| - mistralai/Mistral-7B-Instruct-v0.2 | |
| # Mustra-7B-Instruct-v0.2 | |
| Mustra-7B-Instruct-v0.2 is a merge of the following models using [mergekit](https://github.com/cg123/mergekit): | |
| * [gordicaleksa/YugoGPT](https://huggingface.co/gordicaleksa/YugoGPT) | |
| * [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) | |
| ## 🧩 Configuration | |
| ```yaml | |
| slices: | |
| - sources: | |
| - model: gordicaleksa/YugoGPT | |
| layer_range: [0, 32] | |
| - model: mistralai/Mistral-7B-Instruct-v0.2 | |
| layer_range: [0, 32] | |
| merge_method: slerp | |
| base_model: mistralai/Mistral-7B-Instruct-v0.2 | |
| 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: 0.25 | |
| dtype: bfloat16 | |
| ``` |