| license: apache-2.0 | |
| tags: | |
| - merge | |
| - mergekit | |
| - lazymergekit | |
| - ndavidson/phi-3.1-qlorablend-2 | |
| - ndavidson/phi-3.1-qlora-blend-dpo | |
| # phi-3.1-qlora-blend-dpo-2 | |
| phi-3.1-qlora-blend-dpo-2 is a merge of the following models using [mergekit](https://github.com/cg123/mergekit): | |
| * [ndavidson/phi-3.1-qlorablend-2](https://huggingface.co/ndavidson/phi-3.1-qlorablend-2) | |
| * [ndavidson/phi-3.1-qlora-blend-dpo](https://huggingface.co/ndavidson/phi-3.1-qlora-blend-dpo) | |
| ## 🧩 Configuration | |
| ```yaml | |
| models: | |
| - model: microsoft/Phi-3-mini-4k-instruct | |
| # no parameters necessary for base model | |
| - model: ndavidson/phi-3.1-qlorablend-2 | |
| parameters: | |
| density: 0.5 | |
| weight: 0.5 | |
| - model: ndavidson/phi-3.1-qlora-blend-dpo | |
| parameters: | |
| density: 0.5 | |
| weight: 0.5 | |
| merge_method: ties | |
| base_model: microsoft/Phi-3-mini-4k-instruct | |
| parameters: | |
| normalize: true | |
| dtype: float16 | |
| ``` |