| license: apache-2.0 | |
| tags: | |
| - merge | |
| - mergekit | |
| - lazymergekit | |
| - mlabonne/NeuralHermes-2.5-Mistral-7B | |
| - mistralai/Mistral-7B-Instruct-v0.2 | |
| # mido | |
| mido is a merge of the following models using [mergekit](https://github.com/cg123/mergekit): | |
| * [mlabonne/NeuralHermes-2.5-Mistral-7B](https://huggingface.co/mlabonne/NeuralHermes-2.5-Mistral-7B) | |
| * [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) | |
| ## 🧩 Configuration | |
| ```yaml | |
| models: | |
| - model: mistralai/Mistral-7B-Instruct-v0.2 | |
| # no parameters necessary for base model | |
| - model: mlabonne/NeuralHermes-2.5-Mistral-7B | |
| parameters: | |
| density: 0.5 | |
| weight: 0.5 | |
| - model: mistralai/Mistral-7B-Instruct-v0.2 | |
| parameters: | |
| density: 0.5 | |
| weight: 0.3 | |
| merge_method: ties | |
| base_model: mistralai/Mistral-7B-v0.1 | |
| parameters: | |
| normalize: true | |
| dtype: float16 | |
| ``` |