| --- |
| base_model: |
| - Undi95/PsyMedRP-v1-20B |
| - Undi95/MLewd-ReMM-L2-Chat-20B-Inverted |
| 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 SLERP merge method. |
|
|
| ### Models Merged |
|
|
| The following models were included in the merge: |
| * [Undi95/PsyMedRP-v1-20B](https://huggingface.co/Undi95/PsyMedRP-v1-20B) |
| * [Undi95/MLewd-ReMM-L2-Chat-20B-Inverted](https://huggingface.co/Undi95/MLewd-ReMM-L2-Chat-20B-Inverted) |
|
|
| ### Configuration |
|
|
| The following YAML configuration was used to produce this model: |
|
|
| ```yaml |
| slices: |
| - sources: |
| - model: Undi95/MLewd-ReMM-L2-Chat-20B-Inverted |
| layer_range: [0, 62] # MLewd-ReMM-L2-Chat-20B-Inverted has 62 layers |
| - model: Undi95/PsyMedRP-v1-20B |
| layer_range: [0, 62] # PsyMedRP-v1-20B has 62 layers |
| merge_method: slerp # Or use another method like weight_average if needed |
| base_model: Undi95/PsyMedRP-v1-20B # Can use either as the base model |
| parameters: |
| t: |
| - filter: self_attn |
| value: [0, 0.5, 0.3, 0.7, 1] # Tune these for desired effect |
| - filter: mlp |
| value: [1, 0.5, 0.7, 0.3, 0] |
| - value: 0.5 # Default averaging weight |
| dtype: bfloat16 # Use preferred dtype, like fp16 or float32 if needed |
| ``` |
|
|
