| # Stage 2: Slerp with Lamarck Components [Optimized] | |
| name: MergeStage2v3 | |
| merge_method: slerp | |
| base_model: CultriX/MergeStage1v3 | |
| tokenizer_source: base # Verify and update if needed | |
| dtype: bfloat16 | |
| parameters: | |
| normalize: true | |
| rescale: false | |
| int8_mask: true | |
| int8_mask: true | |
| t: | |
| - value: 0.35 # Adjusted starting value | |
| slices: | |
| - sources: | |
| - model: CultriX/MergeStage1v3 | |
| layer_range: [0, 6] # Example - Adjust based on model architecture | |
| - model: sometimesanotion/Lamarck-14B-v0.7-rc4 | |
| layer_range: [0, 6] # Example - Adjust based on model architecture | |
| - sources: | |
| - model: CultriX/MergeStage1v3 | |
| layer_range: [6, 12] # Example - Adjust based on model architecture | |
| - model: sometimesanotion/Lamarck-14B-v0.7-rc4 | |
| layer_range: [6, 12] # Example - Adjust based on model architecture | |
| - sources: | |
| - model: CultriX/MergeStage1v3 | |
| layer_range: [12, 18] # Example - Adjust based on model architecture | |
| - model: sometimesanotion/Lamarck-14B-v0.7-rc4 | |
| layer_range: [12, 18] # Example - Adjust based on model architecture | |
| - sources: | |
| - model: CultriX/MergeStage1v3 | |
| layer_range: [18, 24] # Example - Adjust based on model architecture | |
| - model: sometimesanotion/Lamarck-14B-v0.7-rc4 | |
| layer_range: [18, 24] # Example - Adjust based on model architecture | |
| - sources: | |
| - model: CultriX/MergeStage1v3 | |
| layer_range: [24, 30] # Example - Adjust based on model architecture | |
| - model: sometimesanotion/Lamarck-14B-v0.7-rc4 | |
| layer_range: [24, 30] # Example - Adjust based on model architecture | |
| - sources: | |
| - model: CultriX/MergeStage1v3 | |
| layer_range: [30, 36] # Example - Adjust based on model architecture | |
| - model: sometimesanotion/Lamarck-14B-v0.7-rc4 | |
| layer_range: [30, 36] # Example - Adjust based on model architecture | |
| - sources: | |
| - model: CultriX/MergeStage1v3 | |
| layer_range: [36, 42] # Example - Adjust based on model architecture | |
| - model: sometimesanotion/Lamarck-14B-v0.7-rc4 | |
| layer_range: [36, 42] # Example - Adjust based on model architecture | |
| - sources: | |
| - model: CultriX/MergeStage1v3 | |
| layer_range: [42, 48] # Example - Adjust based on model architecture | |
| - model: sometimesanotion/Lamarck-14B-v0.7-rc4 | |
| layer_range: [42, 48] # Example - Adjust based on model architectur |