| slices: | |
| - sources: | |
| - model: Undi95/PsyMedRP-v1-20B | |
| layer_range: [0, 62] # PsyMedRP has 62 layers | |
| - model: NeverSleep/Nethena-20B | |
| layer_range: [0, 62] # Nethena-20B has 62 layers | |
| merge_method: slerp # Changing to SLERP method | |
| base_model: Undi95/PsyMedRP-v1-20B # Focus on reasoning from PsyMedRP | |
| parameters: | |
| t: | |
| - filter: self_attn | |
| value: [.3, .6, .9, .6, .3] # smooth gradient of focus | |
| value: [.3, .6, .9, .6, .3] # consistent level of creativity and abstract reasoning | |
| - value: 0.639 | |
| dtype: bfloat16 # Use preferred dtype |