| merge_method: ties # Use TIES for merging multiple models | |
| base_model: Qwen/Qwen2.5-1.5B-Instruct # Base model for the merge | |
| dtype: bfloat16 # Data type for the merged model | |
| models: | |
| - model: Qwen/Qwen2.5-1.5B-Instruct # Base model | |
| parameters: | |
| weight: 0.5 # Weight for the base model | |
| - model: Qwen/Qwen2.5-Math-1.5B-Instruct # Math-focused model | |
| parameters: | |
| density: 0.6 # Retain 60% of significant parameters | |
| weight: 0.3 # Weight for the math model | |
| - model: Qwen/Qwen2.5-Coder-1.5B-Instruct # Code-focused model | |
| parameters: | |
| density: 0.6 # Retain 60% of significant parameters | |
| weight: 0.2 # Weight for the coder model | |
| parameters: | |
| normalize: true # Normalize weights to ensure compatibility | |
| int8_mask: true # Optimize memory and computational efficiency |