| base_model: [] | |
| library_name: transformers | |
| tags: | |
| - mergekit | |
| - merge | |
| # MN-12B-Celeste-V1.9-Instruct | |
| 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 passthrough merge method. | |
| ### Models Merged | |
| The following models were included in the merge: | |
| * g:/11b/Mistral-Nemo-Instruct-2407-12B | |
| * G:/11B/MN-12B-Celeste-V1.9 | |
| ### Configuration | |
| The following YAML configuration was used to produce this model: | |
| ```yaml | |
| # SMB with instruct to help performance. | |
| slices: | |
| - sources: | |
| - model: g:/11b/Mistral-Nemo-Instruct-2407-12B | |
| layer_range: [0, 14] | |
| - sources: | |
| - model: G:/11B/MN-12B-Celeste-V1.9 | |
| layer_range: [8, 24] | |
| parameters: | |
| scale: | |
| - filter: o_proj | |
| value: 1 | |
| - filter: down_proj | |
| value: 1 | |
| - value: 1 | |
| - sources: | |
| - model: g:/11b/Mistral-Nemo-Instruct-2407-12B | |
| layer_range: [14, 22] | |
| parameters: | |
| scale: | |
| - filter: o_proj | |
| value: .5 | |
| - filter: down_proj | |
| value: .5 | |
| - value: 1 | |
| - sources: | |
| - model: g:/11b/Mistral-Nemo-Instruct-2407-12B | |
| layer_range: [22, 31] | |
| parameters: | |
| scale: | |
| - filter: o_proj | |
| value: .75 | |
| - filter: down_proj | |
| value: .75 | |
| - value: 1 | |
| - sources: | |
| - model: G:/11B/MN-12B-Celeste-V1.9 | |
| layer_range: [24, 40] | |
| parameters: | |
| scale: | |
| - filter: o_proj | |
| value: 1 | |
| - filter: down_proj | |
| value: 1 | |
| - value: 1 | |
| merge_method: passthrough | |
| dtype: bfloat16 | |
| ``` | |