merge-test-2-sibling-violation/README.md

base_model, library_name, tags

base_model	library_name	tags
deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B nvidia/Nemotron-Research-Reasoning-Qwen-1.5B nvidia/OpenMath-Nemotron-1.5B Fate-Zero/Archer2.0-Code-1.5B-Preview	transformers	mergekit merge

merge_test_2

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

Merge Details

Merge Method

This model was merged using the DELLA merge method using deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B as a base.

Models Merged

The following models were included in the merge:

• nvidia/Nemotron-Research-Reasoning-Qwen-1.5B
• nvidia/OpenMath-Nemotron-1.5B
• Fate-Zero/Archer2.0-Code-1.5B-Preview

Configuration

The following YAML configuration was used to produce this model:

merge_method: della
base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
dtype: bfloat16
models:
  - model: nvidia/OpenMath-Nemotron-1.5B
    parameters:
      weight: 1.0
      density: 0.6
      epsilon: 0.3
  - model: nvidia/Nemotron-Research-Reasoning-Qwen-1.5B
    parameters:
      weight: 1.0
      density: 0.6
      epsilon: 0.3
  - model: Fate-Zero/Archer2.0-Code-1.5B-Preview
    parameters:
      weight: 1.0
      density: 0.6
      epsilon: 0.3