---
base_model:
- Qwen/QwQ-32B
- Yobenboben/Qwen2.5-32B-Juicy_Snowballs
- spow12/ChatWaifu_32B_reasoning
- trashpanda-org/QwQ-32B-Snowdrop-v0
library_name: transformers
tags:
- mergekit
- merge

---
# Snegs

Tried to fix thinking in the [Snowballs](https://huggingface.co/Yobenboben/Qwen2.5-32B-Juicy_Snowballs) merge, but alas. The context recall is kinda better tho.

**Settings:**

Same as here: https://huggingface.co/Yobenboben/Qwen2.5-32B-Juicy_Snowballs

**Quants:**

https://huggingface.co/mradermacher/Qwen2.5-32B-Snegs-GGUF

## Merge Details
### Merge Method

This model was merged using the [SCE](https://arxiv.org/abs/2408.07990) merge method using [Qwen/QwQ-32B](https://huggingface.co/Qwen/QwQ-32B) as a base.

### Models Merged

The following models were included in the merge:
* [Yobenboben/Qwen2.5-32B-Juicy_Snowballs](https://huggingface.co/Yobenboben/Qwen2.5-32B-Juicy_Snowballs)
* [spow12/ChatWaifu_32B_reasoning](https://huggingface.co/spow12/ChatWaifu_32B_reasoning)
* [trashpanda-org/QwQ-32B-Snowdrop-v0](https://huggingface.co/trashpanda-org/QwQ-32B-Snowdrop-v0)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
merge_method: sce
models:
    - model: trashpanda-org/QwQ-32B-Snowdrop-v0
    - model: spow12/ChatWaifu_32B_reasoning
    - model: Yobenboben/Qwen2.5-32B-Juicy_Snowballs
base_model: Qwen/QwQ-32B
dtype: bfloat16
parameters:
  normalize: true
  int8_mask: true
  select_topk: 1.0
tokenizer_source: base
```