| base_model: jondurbin/bagel-8b-v1.0 | |
| dtype: bfloat16 | |
| merge_method: task_swapping | |
| slices: | |
| - sources: | |
| - layer_range: [0, 32] | |
| model: Gryphe/Pantheon-RP-1.0-8b-Llama-3 | |
| parameters: | |
| diagonal_offset: 2.0 | |
| weight: 0.9 | |
| - layer_range: [0, 32] | |
| model: jondurbin/bagel-8b-v1.0 |