| base_model: | |
| - Nexesenex/mrcuddle_DarkHermes3-Llama3.2-3B-Instruct | |
| - SaisExperiments/Evil-Alpaca-3B-L3.2 | |
| - lunahr/Hermes-3-Llama-3.2-3B-abliterated | |
| 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 [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [Nexesenex/mrcuddle_DarkHermes3-Llama3.2-3B-Instruct](https://huggingface.co/Nexesenex/mrcuddle_DarkHermes3-Llama3.2-3B-Instruct) as a base. | |
| ### Models Merged | |
| The following models were included in the merge: | |
| * [SaisExperiments/Evil-Alpaca-3B-L3.2](https://huggingface.co/SaisExperiments/Evil-Alpaca-3B-L3.2) | |
| * [lunahr/Hermes-3-Llama-3.2-3B-abliterated](https://huggingface.co/lunahr/Hermes-3-Llama-3.2-3B-abliterated) | |
| ### Configuration | |
| The following YAML configuration was used to produce this model: | |
| ```yaml | |
| merge_method: model_stock | |
| models: | |
| - model: SaisExperiments/Evil-Alpaca-3B-L3.2 | |
| parameters: | |
| weight: 1.0 | |
| - model: lunahr/Hermes-3-Llama-3.2-3B-abliterated | |
| parameters: | |
| weight: 1.0 | |
| base_model: Nexesenex/mrcuddle_DarkHermes3-Llama3.2-3B-Instruct | |
| dtype: bfloat16 | |
| normalize: true | |
| ``` | |