| base_model: IlyaGusev/saiga_nemo_12b_sft_m9_d16_simpo_m21_d36_doestoevsky_orpo_m1 | |
| dtype: bfloat16 | |
| merge_method: slerp | |
| parameters: | |
| t: | |
| - filter: self_attn | |
| value: [0.0, 0.5, 0.3, 0.7, 1.0] | |
| - filter: mlp | |
| value: [1.0, 0.5, 0.7, 0.3, 0.0] | |
| - value: 0.5 | |
| slices: | |
| - sources: | |
| - layer_range: [0, 40] | |
| model: IlyaGusev/saiga_nemo_12b_sft_m9_d16_simpo_m21_d36 | |
| - layer_range: [0, 40] | |
| model: IlyaGusev/saiga_nemo_12b_sft_m9_d16_simpo_m21_d36_doestoevsky_orpo_m1 | |