Qwen2.5-7B-R1-Bespoke-Stock

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 huihui-ai/Qwen2.5-7B-Instruct-abliterated-v3 as a base.

Models Merged

The following models were included in the merge:

• bunnycore/Qwen2.5-7B-R1-Bespoke-Task
• deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
• bespokelabs/Bespoke-Stratos-7B

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: bespokelabs/Bespoke-Stratos-7B
  - model: bunnycore/Qwen2.5-7B-R1-Bespoke-Task
  - model: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
  - model: huihui-ai/Qwen2.5-7B-Instruct-abliterated-v3
  
merge_method: model_stock
base_model: huihui-ai/Qwen2.5-7B-Instruct-abliterated-v3
parameters:
    normalize: true
dtype: bfloat16
tokenizer_source: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B