QwQ-R1-Distill-Merge-32B

Testing locally it behaved very well for math problems. It usually starts a problem without the tag, but ends by closing it when using chatml template.

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

Merge Details

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

• /models/Qwen/QwQ-32B
• /models/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B

Configuration

The following YAML configuration was used to produce this model:

base_model: /models/Qwen/QwQ-32B
dtype: bfloat16
merge_method: slerp
parameters:
  t:
  - filter: self_attn
    value: [0.0, 0.5, 0.3, 0.7, 1.0]
  - filter: mlp
    value: [1.0, 0.5, 0.7, 0.3, 0.0]
  - value: 0.5
slices:
- sources:
  - layer_range: [0, 64]
    model: /models/Qwen/QwQ-32B
  - layer_range: [0, 64]
    model: /models/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B