---
base_model:
- ReadyArt/Abomilectrasafemaster-70B
base_model_relation: quantized
library_name: transformers
tags:
- mergekit
- merge
- exl2
- 6-bit

---
# 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 [DARE TIES](https://arxiv.org/abs/2311.03099) merge method using [ReadyArt/Fallen-Abomination-70B-R1-v4.1](https://huggingface.co/ReadyArt/Fallen-Abomination-70B-R1-v4.1) as a base.

### Models Merged

The following models were included in the merge:
* [Tarek07/Dungeonmaster-V2.4-Expanded-LLaMa-70B](https://huggingface.co/Tarek07/Dungeonmaster-V2.4-Expanded-LLaMa-70B)
* [Steelskull/L3.3-Electra-R1-70b](https://huggingface.co/Steelskull/L3.3-Electra-R1-70b)
* [ReadyArt/Fallen-Safeword-70B-R1-v4.1](https://huggingface.co/ReadyArt/Fallen-Safeword-70B-R1-v4.1)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
merge_method: dare_ties
base_model: ReadyArt/Fallen-Abomination-70B-R1-v4.1
models:
  - model: ReadyArt/Fallen-Abomination-70B-R1-v4.1
    parameters:
      weight: 0.3
  - model: Steelskull/L3.3-Electra-R1-70b
    parameters:
      weight: 0.3
  - model: ReadyArt/Fallen-Safeword-70B-R1-v4.1
    parameters:
      weight: 0.2
  - model: Tarek07/Dungeonmaster-V2.4-Expanded-LLaMa-70B
    parameters:
      weight: 0.2
parameters:
  density: 0.3
tokenizer:
  source: union
chat_template: auto
```