Madras1/DeepTron-R1Distil-7B

DeepTron R1: The Ultimate 7B Math Reasoner

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 deepseek-ai/DeepSeek-R1-Distill-Qwen-7B as a base.

Models Merged

The following models were included in the merge:

• nvidia/OpenMath-Nemotron-7B

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
    # Sem parâmetros = Base sólida (Referência)
  - model: nvidia/OpenMath-Nemotron-7B
    parameters:
      density: 0.85  
      weight: 0.3

merge_method: dare_ties
base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
parameters:
  int8_mask: true
dtype: bfloat16