| base_model: meta-llama/Llama-3.2-1B | |
| dtype: float16 | |
| merge_method: nuslerp | |
| modules: | |
| default: | |
| slices: | |
| - sources: | |
| - layer_range: [0, 16] | |
| model: Alelcv27/llama3-1b-math-dpo | |
| parameters: | |
| weight: 0.5 | |
| - layer_range: [0, 16] | |
| model: Alelcv27/llama3-1b-code-dpo | |
| parameters: | |
| weight: 0.5 | |
| - layer_range: [0, 16] | |
| model: meta-llama/Llama-3.2-1B |