YOYO-AI/Qwen2.5-32B-YOYO-reasoning

merge

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

Merge Details

Merge Method

This model was merged using the Model Stock merge method using Qwen/Qwen2.5-32B-Instruct as a base.

Models Merged

The following models were included in the merge:

• maldv/Awqward2.5-32B-Instruct
• qihoo360/Light-R1-32B
• Rombo-Org/Rombo-LLM-V3.0-Qwen-32b
• maldv/Qwentile2.5-32B-Instruct
• Qwen/QwQ-32B
• OpenPipe/Deductive-Reasoning-Qwen-32B

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: Qwen/QwQ-32B
  - model: qihoo360/Light-R1-32B
  - model: maldv/Qwentile2.5-32B-Instruct
  - model: Qwen/Qwen2.5-32B-Instruct
  - model: maldv/Awqward2.5-32B-Instruct
  - model: OpenPipe/Deductive-Reasoning-Qwen-32B
  - model: Rombo-Org/Rombo-LLM-V3.0-Qwen-32b
merge_method: model_stock
base_model: Qwen/Qwen2.5-32B-Instruct
tokenizer_source: base
normalize: true
int8_mask: true
dtype: bfloat16