| base_model: meta-llama/Llama-3.3-70B-Instruct | |
| dtype: bfloat16 | |
| merge_method: dare_ties | |
| parameters: | |
| int8_mask: 1.0 | |
| slices: | |
| - sources: | |
| - layer_range: [0, 80] | |
| model: meta-llama/Llama-3.3-70B-Instruct | |
| - layer_range: [0, 80] | |
| model: Saxo/Linkbricks-Horizon-AI-Japanese-Base-70B | |
| parameters: | |
| density: 0.53 | |
| weight: 0.3 | |
| - layer_range: [0, 80] | |
| model: nitky/Llama-3.1-SuperSwallow-70B-Instruct-v0.1 | |
| parameters: | |
| density: 0.53 | |
| weight: 0.4 | |
| - layer_range: [0, 80] | |
| model: MaziyarPanahi/calme-2.3-llama3.1-70b | |
| parameters: | |
| density: 0.53 | |
| weight: 0.3 | |
| tokenizer_source: union |