| base_model: | |
| - ReadyArt/Forgotten-Safeword-24B | |
| - TheDrummer/Cydonia-24B-v2 | |
| library_name: transformers | |
| tags: | |
| - mergekit | |
| - merge | |
| # merge | |
| This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit). | |
| ## Merge Details | |
| ### Merge Method | |
| This model was merged using the [DARE TIES](https://arxiv.org/abs/2311.03099) merge method using [ReadyArt/Forgotten-Safeword-24B](https://huggingface.co/ReadyArt/Forgotten-Safeword-24B) as a base. | |
| ### Models Merged | |
| The following models were included in the merge: | |
| * [TheDrummer/Cydonia-24B-v2](https://huggingface.co/TheDrummer/Cydonia-24B-v2) | |
| ### Configuration | |
| The following YAML configuration was used to produce this model: | |
| ```yaml | |
| merge_method: dare_ties | |
| base_model: ReadyArt/Forgotten-Safeword-24B | |
| models: | |
| - model: ReadyArt/Forgotten-Safeword-24B | |
| parameters: | |
| weight: 0.5 | |
| density: 0.7 # Balanced parameter retention | |
| - model: TheDrummer/Cydonia-24B-v2 | |
| parameters: | |
| weight: 0.5 | |
| density: 0.7 # Mirror density for symmetry | |
| parameters: | |
| int8_mask: true | |
| normalize: true | |
| lambda: 1.0 # Full task vector application | |
| filter: [] # No layer-specific adjustments | |
| dtype: bfloat16 | |
| tokenizer_source: union | |
| ``` | |