---
base_model:
- ArliAI/Phi-3.5-mini-3.8B-ArliAI-RPMax-v1.1
- MaziyarPanahi/calme-2.1-phi3.5-4b
- bunnycore/Phi-3.5-rp-lora_model
- bunnycore/Phi-3.5-mini-TitanFusion-0.3
- ArliAI/Phi-3.5-mini-3.8B-ArliAI-RPMax-v1.1
- bunnycore/Phi-3.5-rp-lora_model
- bunnycore/Phi-3.5-mini-TitanFusion-0.1
- bunnycore/mergekit-ties-fftkoci
- bunnycore/Phi-3.5-rp-lora_model
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 [ArliAI/Phi-3.5-mini-3.8B-ArliAI-RPMax-v1.1](https://huggingface.co/ArliAI/Phi-3.5-mini-3.8B-ArliAI-RPMax-v1.1) + [bunnycore/Phi-3.5-rp-lora_model](https://huggingface.co/bunnycore/Phi-3.5-rp-lora_model) as a base.

### Models Merged

The following models were included in the merge:
* [ArliAI/Phi-3.5-mini-3.8B-ArliAI-RPMax-v1.1](https://huggingface.co/ArliAI/Phi-3.5-mini-3.8B-ArliAI-RPMax-v1.1)
* [MaziyarPanahi/calme-2.1-phi3.5-4b](https://huggingface.co/MaziyarPanahi/calme-2.1-phi3.5-4b) + [bunnycore/Phi-3.5-rp-lora_model](https://huggingface.co/bunnycore/Phi-3.5-rp-lora_model)
* [bunnycore/Phi-3.5-mini-TitanFusion-0.3](https://huggingface.co/bunnycore/Phi-3.5-mini-TitanFusion-0.3)
* [bunnycore/Phi-3.5-mini-TitanFusion-0.1](https://huggingface.co/bunnycore/Phi-3.5-mini-TitanFusion-0.1)
* [bunnycore/mergekit-ties-fftkoci](https://huggingface.co/bunnycore/mergekit-ties-fftkoci) + [bunnycore/Phi-3.5-rp-lora_model](https://huggingface.co/bunnycore/Phi-3.5-rp-lora_model)

### Configuration

The following YAML configuration was used to produce this model:

```yaml

models:
  - model: bunnycore/Phi-3.5-mini-TitanFusion-0.3
    parameters:
      weight: 1

  - model: bunnycore/Phi-3.5-mini-TitanFusion-0.1
    parameters:
      weight: 1

  - model: MaziyarPanahi/calme-2.1-phi3.5-4b+bunnycore/Phi-3.5-rp-lora_model
    parameters:
      weight: 1

  - model: ArliAI/Phi-3.5-mini-3.8B-ArliAI-RPMax-v1.1
    parameters:
      weight: 1

  - model: bunnycore/mergekit-ties-fftkoci+bunnycore/Phi-3.5-rp-lora_model
    parameters:
      weight: 1

merge_method: ties
base_model: ArliAI/Phi-3.5-mini-3.8B-ArliAI-RPMax-v1.1+bunnycore/Phi-3.5-rp-lora_model
parameters:
  density: 1
  normalize: true
  int8_mask: true
dtype: bfloat16

```