Ourse/R4L

merge

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 bunnycore/Qwen2.5-1.5B-Matrix as a base.

Models Merged

The following models were included in the merge:

• unsloth/Qwen2.5-1.5B-Instruct
• Kukedlc/NeuralQwen-2.5-1.5B-Spanish

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: unsloth/Qwen2.5-1.5B-Instruct
    parameters:
      density: 0.5
      weight: 0.5
  - model: Kukedlc/NeuralQwen-2.5-1.5B-Spanish
    parameters:
      density: 0.5
      weight: 0.5

merge_method: ties
base_model: bunnycore/Qwen2.5-1.5B-Matrix
parameters:
  normalize: false
  int8_mask: true
dtype: float16