| models: | |
| # Base instructed model | |
| - model: unsloth/Qwen2.5-3B-Instruct | |
| parameters: | |
| weight: 1 | |
| density: 1 | |
| # Merged LoRA models | |
| - model: genstruct/merged_model | |
| parameters: | |
| weight: 1.0 | |
| density: 1.0 | |
| # - model: summary/merged_model | |
| # parameters: | |
| # weight: 1.0 | |
| # density: 1.0 | |
| - model: kg/merged_model | |
| parameters: | |
| weight: 1.0 | |
| density: 1.0 | |
| #### THIS BREAKS KG!!! | |
| # - model: pII/merged_model | |
| # parameters: | |
| # weight: 1.0 | |
| # density: 1.0 | |
| # #### Breaks KG! | |
| # - model: preference/merged_model | |
| # parameters: | |
| # weight: 1.0 | |
| # density: 1.0 | |
| - model: triples/merged_model | |
| parameters: | |
| weight: 1.0 | |
| density: 1.0 | |
| # - model: suitable/merged_model | |
| # parameters: | |
| # weight: 1.0 | |
| # density: 1.0 | |
| # - model: feedback/merged_model | |
| # parameters: | |
| # weight: 1.0 | |
| # density: 1.0 | |
| # Merge configuration | |
| merge_method: ties | |
| base_model: unsloth/Qwen2.5-3B | |
| parameters: | |
| normalize: true | |
| int8_mask: true | |
| dtype: bfloat16 | |
| # # Tokenizer configuration | |
| # tokenizer_source: Qwen/Qwen1.5-14B-Chat | |
| # tokenizer_parameters: | |
| # trust_remote_code: true | |
| # # Output configuration | |
| # output: | |
| # precision: bfloat16 | |
| # model_format: safetensors | |
| # max_shard_size: "4GB" | |
| # # Training configuration (for potential fine-tuning) | |
| # training: | |
| # learning_rate: 2e-5 | |
| # warmup_steps: 100 | |
| # gradient_checkpointing: true | |
| # gradient_accumulation_steps: 4 | |
| # # Hardware optimization | |
| # hardware: | |
| # mixed_precision: true | |
| # cuda_memory_fraction: 0.95 | |
| # optimize_model_memory: true |