djuna/DeepSeek-R1-Distill-Qwen-14B-abliterated-remap

merge

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

Merge Details

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

• djuna/Q2.5-Veltha-14B-0.5
• huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated
  - model: djuna/Q2.5-Veltha-14B-0.5
merge_method: slerp
base_model: huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated
parameters:
  t: 0
tokenizer:
  source: "djuna/Q2.5-Veltha-14B-0.5"
  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: 
        model: "huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated"
        kind: "model_token"
        token: "<｜end▁of▁sentence｜>"
      force: true
    <｜User｜>:
      source: 
        model: "huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated"
        kind: "model_token"
        token: "<｜User｜>"
      force: true
    <｜Assistant｜>:
      source: 
        model: "huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated"
        kind: "model_token"
        token: "<｜Assistant｜>"
      force: true
    <｜begin▁of▁sentence｜>:
      source: 
        model: "huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated"
        kind: "model_token"
        token: "<｜begin▁of▁sentence｜>"
      force: true
    <|EOT|>:
      source: 
        model: "huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated"
        kind: "model_token"
        token: "<|EOT|>"
      force: true
    <think>:
      source: 
        model: "huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated"
        kind: "model_token"
        token: "<think>"
      force: true
    </think>:
      source: 
        model: "huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated"
        kind: "model_token"
        token: "</think>"
      force: true
dtype: float32
out_dtype: bfloat16