| dtype: bfloat16 | |
| merge_method: passthrough | |
| slices: | |
| - sources: | |
| - layer_range: [0, 8] | |
| model: nvidia/Mistral-NeMo-Minitron-8B-Base | |
| - sources: | |
| - layer_range: [8, 16] | |
| model: nvidia/Mistral-NeMo-Minitron-8B-Base | |
| parameters: | |
| scale: | |
| - filter: o_proj | |
| value: 0.5 | |
| - filter: down_proj | |
| value: 0.5 | |
| - filter: q_proj | |
| value: 0.85355339059 | |
| - filter: k_proj | |
| value: 0.85355339059 | |
| - value: 1.0 | |
| - sources: | |
| - layer_range: [8, 16] | |
| model: nvidia/Mistral-NeMo-Minitron-8B-Base | |
| parameters: | |
| scale: | |
| - filter: q_proj | |
| value: 0.85355339059 | |
| - filter: k_proj | |
| value: 0.85355339059 | |
| - value: 1.0 | |
| - sources: | |
| - layer_range: [16, 17] | |
| model: nvidia/Mistral-NeMo-Minitron-8B-Base | |
| - sources: | |
| - layer_range: [17, 24] | |
| model: nvidia/Mistral-NeMo-Minitron-8B-Base | |
| parameters: | |
| scale: | |
| - filter: o_proj | |
| value: 0.5 | |
| - filter: down_proj | |
| value: 0.5 | |
| - filter: q_proj | |
| value: 0.85355339059 | |
| - filter: k_proj | |
| value: 0.85355339059 | |
| - value: 1.0 | |
| - sources: | |
| - layer_range: [17, 24] | |
| model: nvidia/Mistral-NeMo-Minitron-8B-Base | |
| parameters: | |
| scale: | |
| - filter: q_proj | |
| value: 0.85355339059 | |
| - filter: k_proj | |
| value: 0.85355339059 | |
| - value: 1.0 | |
| - sources: | |
| - layer_range: [24, 25] | |
| model: nvidia/Mistral-NeMo-Minitron-8B-Base | |
| - sources: | |
| - layer_range: [25, 32] | |
| model: nvidia/Mistral-NeMo-Minitron-8B-Base | |
| parameters: | |
| scale: | |
| - filter: o_proj | |
| value: 0.5 | |
| - filter: down_proj | |
| value: 0.5 | |
| - filter: q_proj | |
| value: 0.85355339059 | |
| - filter: k_proj | |
| value: 0.85355339059 | |
| - value: 1.0 | |
| - sources: | |
| - layer_range: [25, 32] | |
| model: nvidia/Mistral-NeMo-Minitron-8B-Base | |
| parameters: | |
| scale: | |
| - filter: q_proj | |
| value: 0.85355339059 | |
| - filter: k_proj | |
| value: 0.85355339059 | |
| - value: 1.0 | |
| - sources: | |
| - layer_range: [32, 40] | |
| model: nvidia/Mistral-NeMo-Minitron-8B-Base |