CultriX/SeQwence-14Bv4

merge

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

Merge Details

Merge Method

This model was merged using the task arithmetic merge method using Qwen/Qwen2.5-14B-Instruct as a base.

Models Merged

The following models were included in the merge:

• arcee-ai/Virtuoso-Small
• CultriX/Qwen2.5-14B-Wernicke
• CultriX/SeQwence-14B-EvolMerge
• v000000/Qwen2.5-Lumen-14B
• CultriX/SeQwence-14Bv1

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: CultriX/Qwen2.5-14B-Wernicke
    parameters:
      weight: 0.318      # Strong performance in GPQA, MMLU-PRO
      density: 0.6        # Retain 60% of significant parameters
  - model: arcee-ai/Virtuoso-Small
    parameters:
      weight: 0.273      # Exceptional IFEval and MATH Level 5 capabilities
      density: 0.6        # Retain 60% of significant parameters
  - model: CultriX/SeQwence-14B-EvolMerge
    parameters:
      weight: 0.182      # MUSR and balanced contributions to Truthful QA and MMLU
      density: 0.5        # Retain 50% of significant parameters
  - model: CultriX/SeQwence-14Bv1
    parameters:
      weight: 0.136      # Provides diverse data and generalization
      density: 0.4        # Retain 40% of significant parameters
  - model: v000000/Qwen2.5-Lumen-14B
    parameters:
      weight: 0.091      # Enhances creative and narrative tasks
      density: 0.5        # Retain 50% for task diversity
base_model: Qwen/Qwen2.5-14B-Instruct
merge_method: task_arithmetic
parameters:
  normalize: true       # Ensures parameter scaling compatibility
  int8_mask: true       # Optimizes memory and computational efficiency
dtype: bfloat16
tokenizer_source: Qwen/Qwen2.5-14B-Instruct