Sorawiz/Qwen2.5-14B-Instinct-RP

merge

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

Merge Details

Merge Method

This model was merged using the DARE TIES merge method using Sorawiz/Qwen2.5-14B-1M-Instinct as a base.

Models Merged

The following models were included in the merge:

• Ttimofeyka/Tissint-14B-v1.2-128k-RP
• SicariusSicariiStuff/Impish_QWEN_14B-1M
• Sorawiz/Qwen2.5-14B-GCC

Configuration

The following YAML configuration was used to produce this model:

merge_method: dare_ties
base_model: Sorawiz/Qwen2.5-14B-1M-Instinct
models:
  - model: Sorawiz/Qwen2.5-14B-1M-Instinct
    parameters:
      weight: 0.40
  - model: Ttimofeyka/Tissint-14B-v1.2-128k-RP
    parameters:
      weight: 0.25
  - model: SicariusSicariiStuff/Impish_QWEN_14B-1M
    parameters:
      weight: 0.25
  - model: Sorawiz/Qwen2.5-14B-GCC
    parameters:
      weight: 0.10
parameters:
  density: 0.5
tokenizer:
  source: union
chat_template: auto