kairos_14b_v1_m1_uncensored

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 Qwen/Qwen2.5-14B-Instruct as a base.

Models Merged

The following models were included in the merge:

• tanliboy/lambda-qwen2.5-14b-dpo-test
• huihui-ai/Qwen2.5-14B-Instruct-abliterated
• huihui-ai/Qwen2.5-14B-Instruct-abliterated-v2

Configuration

The following YAML configuration was used to produce this model:

merge_method: dare_ties
base_model: Qwen/Qwen2.5-14B-Instruct
tokenizer_source: union
parameters:
  density: 0.5
  weight: 1.0
models:
  - model: huihui-ai/Qwen2.5-14B-Instruct-abliterated-v2
    parameters:
      weight: 0.6
  - model: huihui-ai/Qwen2.5-14B-Instruct-abliterated
    parameters:
      weight: 0.4
  - model: tanliboy/lambda-qwen2.5-14b-dpo-test
    parameters:
      weight: 0.5