| slices: | |
| - sources: | |
| - model: /workspace/HUB_LLM/Llama-3.3-70B-Instruct | |
| layer_range: [0, 80] | |
| - model: /workspace/HUB_LLM/010225_llama33_70b_instruct/checkpoint-1470 | |
| layer_range: [0, 80] | |
| merge_method: slerp | |
| base_model: /workspace/HUB_LLM/Llama-3.3-70B-Instruct | |
| parameters: | |
| t: | |
| - filter: self_attn | |
| value: [0, 0.3, 0.5, 0.7, 1] | |
| - filter: mlp | |
| value: [1, 0.7, 0.5, 0.3, 0] | |
| - value: 0.5 # fallback for rest of tensors | |
| dtype: bfloat16 | |