---
base_model:
- Qwen/Qwen3-32B
- LLMcompe-Team-Watanabe/Qwen3-32B-sft-Deepmath-8k
- LLMcompe-Team-Watanabe/Qwen3-32B-openmathreasoning-sft
library_name: transformers
tags:
- mergekit
- merge

---
# output_model

This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).

## Merge Details
### Merge Method

This model was merged using the [DARE TIES](https://arxiv.org/abs/2311.03099) merge method using [Qwen/Qwen3-32B](https://huggingface.co/Qwen/Qwen3-32B) as a base.

### Models Merged

The following models were included in the merge:
* [LLMcompe-Team-Watanabe/Qwen3-32B-sft-Deepmath-8k](https://huggingface.co/LLMcompe-Team-Watanabe/Qwen3-32B-sft-Deepmath-8k)
* [LLMcompe-Team-Watanabe/Qwen3-32B-openmathreasoning-sft](https://huggingface.co/LLMcompe-Team-Watanabe/Qwen3-32B-openmathreasoning-sft)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
  - model: Qwen/Qwen3-32B
  - model: LLMcompe-Team-Watanabe/Qwen3-32B-sft-Deepmath-8k
    parameters:
      density: 0.53
      weight: 0.3
  - model: LLMcompe-Team-Watanabe/Qwen3-32B-openmathreasoning-sft
    parameters:
      density: 0.53
      weight: 0.7
merge_method: dare_ties
base_model: Qwen/Qwen3-32B
parameters:
  int8_mask: true
  normalize: false
dtype: bfloat16 
```