| slices: | |
| - sources: | |
| - model: deepseek-ai/DeepSeek-R1-Distill-Llama-8B | |
| layer_range: | |
| - 0 | |
| - 32 | |
| - model: MohamedRashad/Arabic-Orpo-Llama-3-8B-Instruct | |
| layer_range: | |
| - 0 | |
| - 32 | |
| merge_method: slerp | |
| base_model: deepseek-ai/DeepSeek-R1-Distill-Llama-8B | |
| parameters: | |
| t: | |
| - filter: self_attn | |
| value: | |
| - 0 | |
| - 0.5 | |
| - 0.3 | |
| - 0.7 | |
| - 1 | |
| - filter: mlp | |
| value: | |
| - 1 | |
| - 0.5 | |
| - 0.7 | |
| - 0.3 | |
| - 0 | |
| - value: 0.5 | |
| dtype: bfloat16 |