| merge_method: ties | |
| base_model: deepcogito/cogito-v1-preview-qwen-14B # Or Qwen2.5, experiment maybe | |
| dtype: bfloat16 # Or float16 if bf16 not well supported | |
| models: | |
| - model: deepcogito/cogito-v1-preview-qwen-14B | |
| # Parameters for TIES - density controls sparsity, weight influences importance | |
| parameters: | |
| density: 0.6 # Start around 0.5-0.7, higher keeps more parameters | |
| weight: 0.6 # Slightly favor cogito for performance | |
| - model: Qwen/Qwen2.5-14B-Instruct-1M | |
| parameters: | |
| density: 0.6 # Keep density consistent usually | |
| weight: 0.4 # Give less weight but allow its parameters to win conflicts where strong |