| | --- |
| | base_model: |
| | - jeiku/Rosa_v1_7B |
| | - jeiku/Rosa_v2_7B |
| | - mlabonne/NeuralMarcoro14-7B |
| | tags: |
| | - mergekit |
| | - merge |
| |
|
| | --- |
| | # Trouble |
| |
|
| | 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](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using [jeiku/Rosa_v1_7B](https://huggingface.co/jeiku/Rosa_v1_7B) as a base. |
| |
|
| | ### Models Merged |
| |
|
| | The following models were included in the merge: |
| | * [jeiku/Rosa_v2_7B](https://huggingface.co/jeiku/Rosa_v2_7B) |
| | * [mlabonne/NeuralMarcoro14-7B](https://huggingface.co/mlabonne/NeuralMarcoro14-7B) |
| |
|
| | ### Configuration |
| |
|
| | The following YAML configuration was used to produce this model: |
| |
|
| | ```yaml |
| | models: |
| | - model: mlabonne/NeuralMarcoro14-7B |
| | parameters: |
| | weight: 0.75 |
| | density: 0.75 |
| | - model: jeiku/Rosa_v2_7B |
| | parameters: |
| | weight: 0.25 |
| | density: 0.25 |
| | merge_method: dare_ties |
| | base_model: jeiku/Rosa_v1_7B |
| | parameters: |
| | dtype: bfloat16 |
| | ``` |
| |
|
