| slices: | |
| - sources: | |
| - model: OpenPipe/mistral-ft-optimized-1218 | |
| layer_range: [0, 32] | |
| - model: mlabonne/NeuralHermes-2.5-Mistral-7B | |
| layer_range: [0, 32] | |
| merge_method: slerp | |
| base_model: OpenPipe/mistral-ft-optimized-1218 | |
| parameters: | |
| t: | |
| - filter: self_attn | |
| value: [0, 0.3, 0.5, 0.7, 0.5, 0.3, 1] # Enhanced: Smoother wave for balanced attention fusion, emphasizing Hermes in mid-layers for reasoning boost | |
| - filter: mlp | |
| value: [1, 0.7, 0.5, 0.3, 0.5, 0.7, 0] # Enhanced: Mirrored wave for MLP, starting strong on Hermes then balancing back | |
| - value: 0.5 # Default remains for other params | |
| normalize: true # Add normalization for stable weights, improving model strength and reducing merge artifacts | |
| density: | |
| - value: 0.6 # Slightly higher density to retain more of the merged structure | |
| - filter: self_attn | |
| value: 0.7 # Bias toward preserving attention details for advanced capabilities | |
| - filter: mlp | |
| value: 0.5 # Balanced for MLP to maintain efficiency | |
| randomize: 0.05 # Small randomization for exploratory strength, can lead to innovative fusions | |
| dtype: bfloat16 | |