| models: | |
| - model: DavidAU/MN-Dark-Planet-TITAN-12B | |
| parameters: | |
| density: 1 | |
| weight: 1 | |
| - model: DavidAU/MN-GRAND-Gutenberg-Lyra4-Lyra-12B-MADNESS | |
| parameters: | |
| density: 1 | |
| weight: 1 | |
| - model: DavidAU/MN-GRAND-Gutenberg-Lyra4-Lyra-12B-DARKNESS | |
| parameters: | |
| density: 1 | |
| weight: 1 | |
| - model: IlyaGusev/saiga_nemo_12b | |
| parameters: | |
| density: 1 | |
| weight: 1 | |
| merge_method: ties | |
| base_model: win10/Mistral-Nemo-abliterated-Nemo-Pro-v2 | |
| dtype: float32 | |
| chat_template: chatml | |
| # Regularization | |
| regularization: | |
| - method: gradient_penalty | |
| scale: 0.05 # Increased influence for gradient control | |
| - method: weight_clipping | |
| clip_range: [-0.2, 0.2] # Broader clipping range for flexibility | |
| - method: random_noise | |
| scale: 0.01 # Stronger noise injection | |
| - method: attention_dropout | |
| scale: 0.1 # Higher dropout to reduce attention fixation | |
| # Postprocessing | |
| postprocessing: | |
| - operation: entropy_regularization | |
| scale: 0.05 # Stronger encouragement for diverse outputs | |
| - operation: non_linear_scaling | |
| parameters: | |
| function: tanh | |
| - operation: sharpening | |
| intensity: 0.5 # Enhanced sharpening for precise outputs | |
| - operation: gaussian_smoothing | |
| sigma: 1.5 # Increased smoothing for stable outputs | |
| - operation: normalize | |
| - operation: dynamic_scaling | |
| scale_range: [0.8, 1.2] # Expanded dynamic range for scaling | |
| - operation: smoothing | |
| parameters: | |
| adaptive: true | |
| range: [0.85, 1.15] # Wider adaptive smoothing range | |
| kernel_size: 5 | |