---
base_model: unsloth/phi-4-unsloth-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
license: apache-2.0
language:
- en
---

This Lora introduces role-playing ability to the PHI-4 model. Now you can make Phi-4 act as any character you want, even the uncensored ones.

# Dataset

```

dataset1 = load_dataset("Nitral-Archive/Project_Persona-ShareGPT", split="train")
dataset2 = load_dataset("alexandreteles/AlpacaToxicQA_ShareGPT", split="train")
dataset3 = load_dataset("Nitral-Archive/Active_RP-ShareGPT", split="train")
dataset4 = load_dataset("Nitral-Archive/AniRecs_QnA-ShareGPT", split="train")
dataset5 = load_dataset("Chaser-cz/sonnet35-charcard-roleplay-sharegpt", split="train")
```

# Uploaded  model

- **Developed by:** bunnycore
- **License:** apache-2.0
- **Finetuned from model :** unsloth/phi-4-unsloth-bnb-4bit

This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.

[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)