R3-Qwen3-8B_merged_ties

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

Merge Details

Merge Method

This model was merged using the TIES merge method using Qwen/Qwen3-8B as a base.

Models Merged

The following models were included in the merge:

• rubricreward/R3-Qwen3-8B-4k
• rubricreward/R3-Qwen3-8B-14k
• rubricreward/R3-Qwen3-8B-LoRA-4k

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: rubricreward/R3-Qwen3-8B-LoRA-4k
    parameters:
      weight: 0.4
  - model: rubricreward/R3-Qwen3-8B-4k
    parameters:
      weight: 0.3
  - model: rubricreward/R3-Qwen3-8B-14k
    parameters:
      weight: 0.3
merge_method: ties
base_model: Qwen/Qwen3-8B
lambda: 1.0
dtype: bfloat16