| --- |
| license: apache-2.0 |
| base_model: |
| - nbeerbower/bruphin-epsilon |
| - cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser |
| tags: |
| - mergekit |
| - merge |
|
|
| --- |
| # bruphin-zeta |
|
|
| This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit). |
|
|
| Rebased off Dolphin 2.6 for correct ChatML support. |
|
|
| ## Merge Details |
| ### Merge Method |
|
|
| This model was merged using the SLERP merge method. |
|
|
| ### Models Merged |
|
|
| The following models were included in the merge: |
| * [nbeerbower/bruphin-epsilon](https://huggingface.co/nbeerbower/bruphin-epsilon) |
| * [cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser](https://huggingface.co/cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser) |
|
|
| ### Configuration |
|
|
| The following YAML configuration was used to produce this model: |
|
|
| ```yaml |
| models: |
| - model: nbeerbower/bruphin-epsilon |
| layer_range: [0, 32] |
| - model: cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser |
| layer_range: [0, 32] |
| merge_method: slerp |
| base_model: cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser |
| parameters: |
| t: |
| - filter: self_attn |
| value: [0, 0.5, 0.3, 0.7, 1] |
| - filter: mlp |
| value: [1, 0.5, 0.7, 0.3, 0] |
| - value: 0.5 |
| dtype: bfloat16 |
| |
| ``` |
|
|
