LLMcompe-Team-Watanabe/Qwen3-32B-merge-ensemble

qwen32b_ensemble_output

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/Qwen3-32B as a base.

Models Merged

The following models were included in the merge:

• LLMcompe-Team-Watanabe/Qwen3-32B-merge-base3-math3-physics3-others1
• LLMcompe-Team-Watanabe/Qwen3-32B-merge-math4-science4-submath05-med05-other1
• LLMcompe-Team-Watanabe/Qwen3-32B-merge-base4-math3-physics3
• LLMcompe-Team-Watanabe/Qwen3-32B-openmathreasoning-sft
• LLMcompe-Team-Watanabe/Qwen3-32B-merge-base2-math3-science3-submath05-med05-other1

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: Qwen/Qwen3-32B
  - model: LLMcompe-Team-Watanabe/Qwen3-32B-merge-base2-math3-science3-submath05-med05-other1
    parameters:
      density: 0.53
      weight: 0.20
  - model: LLMcompe-Team-Watanabe/Qwen3-32B-merge-base3-math3-physics3-others1
    parameters:
      density: 0.53
      weight: 0.20
  - model: LLMcompe-Team-Watanabe/Qwen3-32B-merge-base4-math3-physics3
    parameters:
      density: 0.53
      weight: 0.15
  - model: LLMcompe-Team-Watanabe/Qwen3-32B-merge-math4-science4-submath05-med05-other1
    parameters:
      density: 0.53
      weight: 0.15
  - model: LLMcompe-Team-Watanabe/Qwen3-32B-openmathreasoning-sft
    parameters:
      density: 0.50
      weight: 0.15
  - model: Qwen/Qwen3-32B
    parameters:
      density: 0.53
      weight: 0.15
merge_method: dare_ties
base_model: Qwen/Qwen3-32B
parameters:
  int8_mask: true
  normalize: false
dtype: bfloat16