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

---
# prototype-0.4x87

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/prototype-0.4x83 as a base.

### Models Merged

The following models were included in the merge:
* /workspace/cache/models--Sao10K--70B-L3.3-Cirrus-x1/snapshots/31d7ca33f3098d1eabe6f87a2c5b5bde85b20f35
* /workspace/prototype-0.4x85
* /workspace/cache/models--ReadyArt--Forgotten-Safeword-70B-v5.0/snapshots/ac2650005a6fdef7f4cd62590dcb665155349a5b
* /workspace/cache/models--LatitudeGames--Wayfarer-Large-70B-Llama-3.3/snapshots/68cb7a33f692be64d4b146576838be85593a7459

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
  - model: /workspace/cache/models--LatitudeGames--Wayfarer-Large-70B-Llama-3.3/snapshots/68cb7a33f692be64d4b146576838be85593a7459
    parameters:
      select_topk: 0.15
  - model: /workspace/cache/models--ReadyArt--Forgotten-Safeword-70B-v5.0/snapshots/ac2650005a6fdef7f4cd62590dcb665155349a5b
    parameters:
      select_topk: 0.23
  - model: /workspace/cache/models--Sao10K--70B-L3.3-Cirrus-x1/snapshots/31d7ca33f3098d1eabe6f87a2c5b5bde85b20f35
    parameters:
      select_topk: 0.3
  - model: /workspace/prototype-0.4x85
    parameters:
      select_topk: 0.4
  - model: /workspace/prototype-0.4x83
    parameters:
      select_topk: 0.55
base_model: /workspace/prototype-0.4x83
merge_method: sce
tokenizer:
  source: union
chat_template: llama3
int8_mask: true
dtype: bfloat16
```