| base_model: grimjim/Llama-3-Instruct-8B-SPPO-Iter3-SimPO-merge | |
| dtype: bfloat16 | |
| merge_method: task_arithmetic | |
| parameters: | |
| normalize: false | |
| slices: | |
| - sources: | |
| - layer_range: [0, 32] | |
| model: grimjim/Llama-3-Instruct-8B-SPPO-Iter3-SimPO-merge | |
| - layer_range: [0, 32] | |
| model: tokyotech-llm/Llama-3-Swallow-8B-Instruct-v0.1 | |
| parameters: | |
| weight: 0.1 | |