---
base_model:
- ArliAI/Llama-3.3-70B-ArliAI-RPMax-v1.4
- huihui-ai/DeepSeek-R1-Distill-Llama-70B-abliterated
- LatitudeGames/Wayfarer-Large-70B-Llama-3.3
- Sao10K/Llama-3.3-70B-Vulpecula-r1
- TareksLab/Doppleganger-V3-LLaMa-70B
library_name: transformers
tags:
- mergekit
- merge

---
# MERGE2

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 [Linear DELLA](https://arxiv.org/abs/2406.11617) merge method using [Sao10K/Llama-3.3-70B-Vulpecula-r1](https://huggingface.co/Sao10K/Llama-3.3-70B-Vulpecula-r1) as a base.

### Models Merged

The following models were included in the merge:
* [ArliAI/Llama-3.3-70B-ArliAI-RPMax-v1.4](https://huggingface.co/ArliAI/Llama-3.3-70B-ArliAI-RPMax-v1.4)
* [huihui-ai/DeepSeek-R1-Distill-Llama-70B-abliterated](https://huggingface.co/huihui-ai/DeepSeek-R1-Distill-Llama-70B-abliterated)
* [LatitudeGames/Wayfarer-Large-70B-Llama-3.3](https://huggingface.co/LatitudeGames/Wayfarer-Large-70B-Llama-3.3)
* [TareksLab/Doppleganger-V3-LLaMa-70B](https://huggingface.co/TareksLab/Doppleganger-V3-LLaMa-70B)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
  - model: huihui-ai/DeepSeek-R1-Distill-Llama-70B-abliterated
    parameters:
      weight: 0.20
      density: 0.7
      epsilon: 0.20
      lambda: 1.1
  - model: ArliAI/Llama-3.3-70B-ArliAI-RPMax-v1.4
    parameters:
      weight: 0.20
      density: 0.7
      epsilon: 0.20
      lambda: 1.1
  - model: LatitudeGames/Wayfarer-Large-70B-Llama-3.3
    parameters:
      weight: 0.20
      density: 0.7
      epsilon: 0.20
      lambda: 1.1
  - model: TareksLab/Doppleganger-V3-LLaMa-70B
    parameters:
      weight: 0.20
      density: 0.7
      epsilon: 0.20
      lambda: 1.1
  - model: Sao10K/Llama-3.3-70B-Vulpecula-r1
    parameters:
      weight: 0.20
      density: 0.7
      epsilon: 0.20
      lambda: 1.1
merge_method: della_linear
base_model: Sao10K/Llama-3.3-70B-Vulpecula-r1
parameters:
  normalize: false
  int8_mask: true
dtype: bfloat16
chat_template: llama3
tokenizer:
 source: base

```