| models: | |
| - model: FuseAI/FuseO1-DeepSeekR1-QwQ-SkyT1-32B-Preview | |
| parameters: | |
| weight: 1.2 # Slightly favor | |
| density: 0.9 # Sparsified a bit to reduce noise | |
| - model: FuseAI/FuseO1-DeepSeekR1-Qwen2.5-Coder-32B-Preview | |
| parameters: | |
| weight: 1 | |
| density: 0.9 | |
| - model: FuseAI/FuseO1-DeepSeekR1-QwQ-SkyT1-Flash-32B-Preview | |
| parameters: | |
| weight: 1 | |
| density: 0.9 | |
| merge_method: sce # SCE for adaptive weighting | |
| base_model: Rombo-Org/Rombo-LLM-V3.1-QWQ-32b | |
| parameters: | |
| normalize: true | |
| int8_mask: true | |
| select_topk: 0.1 # Retain the top 10% high-variance elements | |
| tokenizer_source: union # Union to combine vocabularies | |
| dtype: bfloat16 |