---
base_model:
- mergekit-community/ignore_Marigold-v0-NOBASE
- cs2764/QwQ-R1984-32B-h-novel
- mergekit-community/ignore_clush-stage2-NOBASE
- mergekit-community/ignore_Marigold-v1-NOBASE
library_name: transformers
tags:
- mergekit
- merge

---
# merge

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 [TIES](https://arxiv.org/abs/2306.01708) merge method using [cs2764/QwQ-R1984-32B-h-novel](https://huggingface.co/cs2764/QwQ-R1984-32B-h-novel) as a base.

### Models Merged

The following models were included in the merge:
* [mergekit-community/ignore_Marigold-v0-NOBASE](https://huggingface.co/mergekit-community/ignore_Marigold-v0-NOBASE)
* [mergekit-community/ignore_clush-stage2-NOBASE](https://huggingface.co/mergekit-community/ignore_clush-stage2-NOBASE)
* [mergekit-community/ignore_Marigold-v1-NOBASE](https://huggingface.co/mergekit-community/ignore_Marigold-v1-NOBASE)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
  # Base
  - model: cs2764/QwQ-R1984-32B-h-novel
    parameters:
      weight: 1.0
  # Models
  - model: mergekit-community/ignore_clush-stage2-NOBASE
    parameters:
      density: 0.35
      weight: 13e-5
  - model: mergekit-community/ignore_Marigold-v0-NOBASE
    parameters:
      density: 0.85
      weight: 25e-5
  - model: mergekit-community/ignore_Marigold-v1-NOBASE
    parameters:
      density: 0.85
      weight: 25e-5
merge_method: ties
base_model: cs2764/QwQ-R1984-32B-h-novel
parameters:
  normalize: false
  int8_mask: false
dtype: float32
out_dtype: bfloat16
```