djuna/TEST-Q2.5-Lenned-14B

merge

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

Merge Details

Merge Method

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

Models Merged

The following models were included in the merge:

• Krystalan/DRT-o1-14B
• djuna/Q2.5-Veltha-14B-0.5
• huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated
• netease-youdao/Confucius-o1-14B

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: Qwen/Qwen2.5-14B
  - model: netease-youdao/Confucius-o1-14B
  - model: djuna/Q2.5-Veltha-14B-0.5
  - model: Krystalan/DRT-o1-14B
  - model: huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated
merge_method: sce
base_model: Qwen/Qwen2.5-14B
tokenizer:
  source: "union"
  tokens: 
    <|endoftext|>:
      source: "djuna/Q2.5-Veltha-14B-0.5"
    <|im_start|>:
      source: "djuna/Q2.5-Veltha-14B-0.5"
    <|im_end|>:
      source: "djuna/Q2.5-Veltha-14B-0.5"
    <|object_ref_start|>:
      source: "djuna/Q2.5-Veltha-14B-0.5"
    <|object_ref_end|>:
      source: "djuna/Q2.5-Veltha-14B-0.5"
    <|box_start|>:
      source: "djuna/Q2.5-Veltha-14B-0.5"
    <|box_end|>:
      source: "djuna/Q2.5-Veltha-14B-0.5"
    <｜end▁of▁sentence｜>:
      source: "huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated"
      force: true
    <｜User｜>:
      source: "huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated"
      force: true
    <｜Assistant｜>:
      source: "huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated"
      force: true
    <｜begin▁of▁sentence｜>:
      source: "huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated"
      force: true
    <|EOT|>:
      source: "huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated"
      force: true
    <think>:
      source: "huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated"
      force: true
    </think>:
      source: "huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated"
      force: true
dtype: float32
out_dtype: bfloat16