| slices: | |
| - sources: | |
| - model: rwitz/experiment26-truthy-iter-1 | |
| layer_range: [0, 32] | |
| - model: chihoonlee10/T3Q-Mistral-Orca-Math-DPO | |
| layer_range: [0, 32] | |
| merge_method: slerp | |
| base_model: rwitz/experiment26-truthy-iter-1 | |
| 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 | |
| random_seed: 0 | |