| slices: | |
| - sources: | |
| - model: CorticalStack/pastiche-crown-clown-7b-dare-dpo | |
| layer_range: [0, 32] | |
| - model: MSL7/INEX12-7b | |
| layer_range: [0, 32] | |
| merge_method: slerp | |
| base_model: CorticalStack/pastiche-crown-clown-7b-dare-dpo | |
| 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 | |
| slices: | |
| - sources: | |
| - model: liminerity/M7-7b | |
| layer_range: [0, 32] | |
| - model: CorticalStack/pastiche-crown-clown-7b-dare-dpo | |
| layer_range: [0, 32] | |
| merge_method: slerp | |
| base_model: liminerity/M7-7b | |
| 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 | |
| slices: | |
| - sources: | |
| - model: ammarali32/multi_verse_model | |
| layer_range: [0, 32] | |
| - model: liminerity/merge | |
| layer_range: [0, 32] | |
| merge_method: slerp | |
| base_model: ammarali32/multi_verse_model | |
| 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 | |
| slices: | |
| - sources: | |
| - model: Gille/StrangeMerges_32-7B-slerp | |
| layer_range: [0, 32] | |
| - model: yam-peleg/Experiment26-7B | |
| layer_range: [0, 32] | |
| merge_method: slerp | |
| base_model: Gille/StrangeMerges_32-7B-slerp | |
| 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 | |