Edens-Gate/qwendaledingle-14b-della-testing

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 Orion-zhen/Qwen2.5-14B-Instruct-Uncensored as a base.

Models Merged

The following models were included in the merge:

• allura-org/TQ2.5-14B-Sugarquill-v1
• EVA-UNIT-01/EVA-Qwen2.5-14B-v0.2
• Qwen/Qwen2.5-14B-Instruct
• Orion-zhen/Meissa-Qwen2.5-14B-Instruct

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: Qwen/Qwen2.5-14B-Instruct
    parameters:
      weight: 0.1
      density: 0.4
  - model: Orion-zhen/Meissa-Qwen2.5-14B-Instruct
    parameters:
      weight: 0.12
      density: 0.5
  - model: EVA-UNIT-01/EVA-Qwen2.5-14B-v0.2
    parameters:
      weight: 0.2
      density: 0.6
  - model: allura-org/TQ2.5-14B-Sugarquill-v1
    parameters:
      weight: 0.45
      density: 0.7
merge_method: della_linear
base_model: Orion-zhen/Qwen2.5-14B-Instruct-Uncensored
parameters:
  epsilon: 0.05
  lambda: 1
dtype: bfloat16
tokenizer_source: base