| name: OptimalMerge-14B | |
| merge_method: dare_ties | |
| base_model: suayptalha/Lamarckvergence-14B | |
| tokenizer_source: base | |
| dtype: bfloat16 | |
| out_dtype: bfloat16 | |
| parameters: | |
| normalize: true | |
| int8_mask: true | |
| models: | |
| - model: suayptalha/Lamarckvergence-14B | |
| parameters: | |
| weight: 0.35 | |
| density: 0.75 | |
| - model: sthenno/tempesthenno-ppo-ckpt40 | |
| parameters: | |
| weight: 0.25 | |
| density: 0.7 | |
| - model: tanliboy/lambda-qwen2.5-14b-dpo-test | |
| parameters: | |
| weight: 0.2 | |
| density: 0.65 | |
| - model: djuna/Q2.5-Veltha-14B | |
| parameters: | |
| weight: 0.1 | |
| density: 0.6 | |
| - model: Goekdeniz-Guelmez/Josiefied-Qwen2.5-14B-Instruct-abliterated-v4 | |
| parameters: | |
| weight: 0.1 | |
| density: 0.6 | |
| adaptive_merge_parameters: | |
| task_weights: | |
| IFEval: 1.8 | |
| BBH: 1.5 | |
| MATH: 2.0 | |
| GPQA: 1.4 | |
| MUSR: 1.3 | |
| MMLU-PRO: 1.5 | |
| smoothing_factor: 0.1 | |
| gradient_clipping: | |
| suayptalha/Lamarckvergence-14B: 0.85 | |
| sthenno/tempesthenno-ppo-ckpt40: 0.88 | |
| tanliboy/lambda-qwen2.5-14b-dpo-test: 0.87 | |
| djuna/Q2.5-Veltha-14B: 0.89 | |
| Goekdeniz-Guelmez/Josiefied-Qwen2.5-14B-Instruct-abliterated-v4: 0.86 |