README.md

metadata

base_model:
  - zetasepic/Qwen2.5-32B-Instruct-abliterated-v2
  - Qwen/QwQ-32B
  - Qwen/Qwen2.5-32B-Instruct
library_name: transformers
tags:
  - mergekit
  - merge

More recommended DataSoul/QAQ-32B-merge3 But it is still not a 'thinking' model.

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/QwQ-32B as a base.

Models Merged

The following models were included in the merge:

• zetasepic/Qwen2.5-32B-Instruct-abliterated-v2
• Qwen/Qwen2.5-32B-Instruct

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: Qwen/QwQ-32B
    #no parameters necessary for base model
  - model: zetasepic/Qwen2.5-32B-Instruct-abliterated-v2
    parameters:
      weight: 1
      density: 1
  - model: Qwen/Qwen2.5-32B-Instruct
    parameters:
      weight: -1
      density: 1
merge_method: ties
base_model: Qwen/QwQ-32B
parameters:
  normalize: true
  int8_mask: true
dtype: float16