| NEXT TRIAL: make WizardLM into a 20B and SLERP it with XwinXtended? maybe.... | |
| slices: | |
| - sources: | |
| - model: seb-c/Psydestroyer-20B | |
| layer_range: [0, 62] | |
| - model: Elfrino/XwinXtended-20B | |
| layer_range: [0, 62] | |
| merge_method: slerp | |
| base_model: seb-c/Psydestroyer-20B | |
| parameters: | |
| t: | |
| - filter: self_attn | |
| value: [0.8, 0.8, 0.9, 0.7, .8] | |
| - filter: mlp | |
| value: [.8, 0.8, 0.9, 0.8, .7] | |
| - value: 0.3369 | |
| dtype: bfloat16 |