mergekit-community/mergekit-model_stock-pjdbpjk

merge

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

Merge Details

Merge Method

This model was merged using the Model Stock merge method using deepseek-ai/DeepSeek-R1-Distill-Qwen-32B as a base.

Models Merged

The following models were included in the merge:

• Sao10K/32B-Qwen2.5-Kunou-v1
• ArliAI/Qwen2.5-32B-ArliAI-RPMax-v1.3
• EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2
  - model: ArliAI/Qwen2.5-32B-ArliAI-RPMax-v1.3
  - model: Sao10K/32B-Qwen2.5-Kunou-v1
merge_method: model_stock
base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
parameters:
  filter_wise: false
dtype: bfloat16
tokenizer:
  source: union
  tokens:

    <｜end▁of▁sentence｜>:
      source:
        kind: "model_token"
        model: "EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2"
        token: "<|endoftext|>"

    <｜end▁of▁sentence｜>:
      source:
        kind: "model_token"
        model: "ArliAI/Qwen2.5-32B-ArliAI-RPMax-v1.3"
        token: "<|endoftext|>"

    <｜end▁of▁sentence｜>:
      source:
        kind: "model_token"
        model: "Sao10K/32B-Qwen2.5-Kunou-v1"
        token: "<|endoftext|>"

    <｜begin▁of▁sentence｜>:
      source:
        kind: "model_token"
        model: "EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2"
        token: "<|object_ref_start|>"

    <｜begin▁of▁sentence｜>:
      source:
        kind: "model_token"
        model: "ArliAI/Qwen2.5-32B-ArliAI-RPMax-v1.3"
        token: "<|object_ref_start|>"

    <｜begin▁of▁sentence｜>:
      source:
        kind: "model_token"
        model: "Sao10K/32B-Qwen2.5-Kunou-v1"
        token: "<|object_ref_start|>"

    <｜User｜>:
      source:
        kind: "model_token"
        model: "EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2"
        token: "<|im_start|>"

    <｜User｜>:
      source:
        kind: "model_token"
        model: "ArliAI/Qwen2.5-32B-ArliAI-RPMax-v1.3"
        token: "<|im_start|>"

    <｜User｜>:
      source:
        kind: "model_token"
        model: "Sao10K/32B-Qwen2.5-Kunou-v1"
        token: "<|im_start|>"

    <｜Assistant｜>:
      source:
        kind: "model_token"
        model: "EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2"
        token: "<|im_end|>"

    <｜Assistant｜>:
      source:
        kind: "model_token"
        model: "ArliAI/Qwen2.5-32B-ArliAI-RPMax-v1.3"
        token: "<|im_end|>"

    <｜Assistant｜>:
      source:
        kind: "model_token"
        model: "Sao10K/32B-Qwen2.5-Kunou-v1"
        token: "<|im_end|>"

    <think>:
      source:
        kind: "model_token"
        model: "EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2"
        token: "<|box_start|>"

    <think>:
      source:
        kind: "model_token"
        model: "ArliAI/Qwen2.5-32B-ArliAI-RPMax-v1.3"
        token: "<|box_start|>"

    <think>:
      source:
        kind: "model_token"
        model: "Sao10K/32B-Qwen2.5-Kunou-v1"
        token: "<|box_start|>"

    </think>:
      source:
        kind: "model_token"
        model: "EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2"
        token: "<|box_end|>"

    </think>:
      source:
        kind: "model_token"
        model: "ArliAI/Qwen2.5-32B-ArliAI-RPMax-v1.3"
        token: "<|box_end|>"

    </think>:
      source:
        kind: "model_token"
        model: "Sao10K/32B-Qwen2.5-Kunou-v1"
        token: "<|box_end|>"