ehristoforu/ud-14b

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 Qwen/Qwen2.5-32B as a base.

Models Merged

The following models were included in the merge:

• Qwen/QwQ-32B-Preview
• unsloth/DeepSeek-R1-Distill-Qwen-32B

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: unsloth/DeepSeek-R1-Distill-Qwen-32B
    parameters:
      weight: 0.65
      density: 0.65
  - model: Qwen/QwQ-32B-Preview
    parameters:
      weight: 0.35
      density: 0.35
merge_method: ties
base_model: Qwen/Qwen2.5-32B
parameters:
  normalize: true
  int8_mask: true
tokenizer_source: "unsloth/DeepSeek-R1-Distill-Qwen-32B"
dtype: float16