Phi-4-Chat / README.md
Sorawiz's picture
Upload folder using huggingface_hub
df2c2e6 verified
---
base_model:
- Sorawiz/Phi-4-Base
- Sorawiz/Phi-4-Empathetic-Abliterated
- bunnycore/Phi-4-RP-lora_model
- Sorawiz/Phi-4-Empathetic-Abliterated
- bunnycore/Phi-4-rp-v1-lora
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 [Sorawiz/Phi-4-Base](https://huggingface.co./Sorawiz/Phi-4-Base) as a base.
### Models Merged
The following models were included in the merge:
* [Sorawiz/Phi-4-Empathetic-Abliterated](https://huggingface.co./Sorawiz/Phi-4-Empathetic-Abliterated) + [bunnycore/Phi-4-RP-lora_model](https://huggingface.co./bunnycore/Phi-4-RP-lora_model)
* [Sorawiz/Phi-4-Empathetic-Abliterated](https://huggingface.co./Sorawiz/Phi-4-Empathetic-Abliterated) + [bunnycore/Phi-4-rp-v1-lora](https://huggingface.co./bunnycore/Phi-4-rp-v1-lora)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
models:
- model: Sorawiz/Phi-4-Base
- model: Sorawiz/Phi-4-Empathetic-Abliterated+bunnycore/Phi-4-RP-lora_model
parameters:
density: 0.50
weight: 0.50
- model: Sorawiz/Phi-4-Empathetic-Abliterated+bunnycore/Phi-4-rp-v1-lora
parameters:
density: 0.50
weight: 0.50
merge_method: ties
base_model: Sorawiz/Phi-4-Base
parameters:
normalize: true
dytpe: float32
```