thiflaf/Qwen3-4B-Instruct-Thinking-SLERP

merged_model

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:

• Qwen/Qwen3-4B-Instruct-2507
• Qwen/Qwen3-4B-Thinking-2507

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
      - model: Qwen/Qwen3-4B-Instruct-2507
        layer_range: [0, 32]
      - model: Qwen/Qwen3-4B-Thinking-2507
        layer_range: [0, 32]
merge_method: slerp
base_model: Qwen/Qwen3-4B-Instruct-2507
parameters:
  t:
    - filter: self_attn
      value: 0.5
    - filter: mlp
      value: 0.5
    - value: 0.5
dtype: bfloat16