| dtype: bfloat16 | |
| merge_method: passthrough | |
| slices: | |
| - sources: | |
| - layer_range: [0, 4] | |
| model: allenai/OLMoE-1B-7B-0125-Instruct | |
| - sources: | |
| - layer_range: [4, 6] | |
| model: allenai/OLMoE-1B-7B-0125-Instruct | |
| - sources: | |
| - layer_range: [4, 6] | |
| model: allenai/OLMoE-1B-7B-0125-Instruct | |
| parameters: | |
| scale: | |
| - filter: o_proj | |
| value: 0.0 | |
| - filter: down_proj | |
| value: 0.0 | |
| - value: 1.0 | |
| - sources: | |
| - layer_range: [6, 8] | |
| model: allenai/OLMoE-1B-7B-0125-Instruct | |
| - sources: | |
| - layer_range: [6, 8] | |
| model: allenai/OLMoE-1B-7B-0125-Instruct | |
| parameters: | |
| scale: | |
| - filter: o_proj | |
| value: 0.0 | |
| - filter: down_proj | |
| value: 0.0 | |
| - value: 1.0 | |
| - sources: | |
| - layer_range: [8, 10] | |
| model: allenai/OLMoE-1B-7B-0125-Instruct | |
| - sources: | |
| - layer_range: [8, 10] | |
| model: allenai/OLMoE-1B-7B-0125-Instruct | |
| parameters: | |
| scale: | |
| - filter: o_proj | |
| value: 0.0 | |
| - filter: down_proj | |
| value: 0.0 | |
| - value: 1.0 | |
| - sources: | |
| - layer_range: [10, 12] | |
| model: allenai/OLMoE-1B-7B-0125-Instruct | |
| - sources: | |
| - layer_range: [10, 12] | |
| model: allenai/OLMoE-1B-7B-0125-Instruct | |
| parameters: | |
| scale: | |
| - filter: o_proj | |
| value: 0.0 | |
| - filter: down_proj | |
| value: 0.0 | |
| - value: 1.0 | |
| - sources: | |
| - layer_range: [12, 16] | |
| model: allenai/OLMoE-1B-7B-0125-Instruct | |