Sakalti/mergekit-della_linear-vmeykci

merge

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the della_linear merge method using bunnycore/Qwen2.5-7B-RRP-1M as a base.

Models Merged

The following models were included in the merge:

• AXCXEPT/Qwen2.5-Math-7B-Instruct-jp-EZO_OREO

Configuration

The following YAML configuration was used to produce this model:

merge_method: della_linear
base_model: bunnycore/Qwen2.5-7B-RRP-1M
dtype: float16
parameters:
  epsilon: 0.015            # Fine-grain scaling for precision.
  lambda: 1.6               # Strong emphasis on top-performing models.
  normalize: true           # Stable parameter integration across models.
adaptive_merge_parameters:
  task_weights:
    tinyArc: 1.75           # Logical reasoning.
    tinyHellaswag: 1.65     # Contextual predictions.
    tinyMMLU: 1.8           # Domain knowledge.
    tinyTruthfulQA: 2.0     # Prioritize truthful reasoning.
    tinyTruthfulQA_mc1: 1.85
    tinyWinogrande: 1.9     # Advanced reasoning and predictions.
    IFEval: 2.1             # Instruction-following and multitasking.
    BBH: 1.9                # Complex reasoning.
    MATH: 2.3               # Mathematical reasoning.
    GPQA: 2.2             # Factual QA.
    MUSR: 2.0             # Multi-step reasoning.
    MMLU-PRO: 2.2       # Domain multitask performance.
  smoothing_factor: 0.1     # Smooth blending across benchmarks.
models:
 - model: AXCXEPT/Qwen2.5-Math-7B-Instruct-jp-EZO_OREO
   parameters:
      weight: 1
      density: 1