---
base_model: []
library_name: transformers
tags:
- mergekit
- merge

---
# base

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 [SCE](https://arxiv.org/abs/2408.07990) merge method using /workspace/cache/models--TheDrummer--L3.3-Interleaved-Upscale-105B/snapshots/dc1c192564ddf43133a71a7bdc8e6e91c69a2835 as a base.

### Models Merged

The following models were included in the merge:
* /workspace/magnum2
* /workspace/nemo2
* /workspace/hydro2

### Configuration

The following YAML configuration was used to produce this model:

```yaml
base_model: /workspace/cache/models--TheDrummer--L3.3-Interleaved-Upscale-105B/snapshots/dc1c192564ddf43133a71a7bdc8e6e91c69a2835
chat_template: llama3
dtype: float32
merge_method: sce
modules:
  default:
    slices:
    - sources:
      - layer_range: [0, 120]
        model: /workspace/hydro2
        parameters:
          select_topk: 0.5
      - layer_range: [0, 120]
        model: /workspace/nemo2
        parameters:
          select_topk: 0.4
      - layer_range: [0, 120]
        model: /workspace/magnum2
        parameters:
          select_topk: 0.3
      - layer_range: [0, 120]
        model: /workspace/cache/models--TheDrummer--L3.3-Interleaved-Upscale-105B/snapshots/dc1c192564ddf43133a71a7bdc8e6e91c69a2835
        parameters:
          select_topk: 0.4
out_dtype: bfloat16
parameters:
  int8_mask: 1.0
tokenizer:
  source: base
```