Instructions to use bunnycore/Phi-4-RP-V0.2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bunnycore/Phi-4-RP-V0.2 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="bunnycore/Phi-4-RP-V0.2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("bunnycore/Phi-4-RP-V0.2")
model = AutoModelForCausalLM.from_pretrained("bunnycore/Phi-4-RP-V0.2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use bunnycore/Phi-4-RP-V0.2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bunnycore/Phi-4-RP-V0.2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bunnycore/Phi-4-RP-V0.2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/bunnycore/Phi-4-RP-V0.2

SGLang

How to use bunnycore/Phi-4-RP-V0.2 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "bunnycore/Phi-4-RP-V0.2" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bunnycore/Phi-4-RP-V0.2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "bunnycore/Phi-4-RP-V0.2" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bunnycore/Phi-4-RP-V0.2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use bunnycore/Phi-4-RP-V0.2 with Docker Model Runner:
```
docker model run hf.co/bunnycore/Phi-4-RP-V0.2
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Phi-4-RP-V0.2 is based on the Phi-4 architecture, which is a state-of-the-art large language model designed to handle a wide range of natural language tasks with high efficiency and performance.

Primary Use Cases

Interactive Storytelling : Engage users in dynamic, immersive stories where they can take on different roles and make choices that influence the narrative.
Role-Playing Games (RPGs) : Provide rich, interactive experiences in RPGs, enhancing gameplay through intelligent character interactions.
Virtual Assistants : Offer personalized, engaging conversations that simulate human-like interactions for customer support or entertainment purposes.

Training Data

Phi-4-RP-V0.2 is specifically trained on role-playing datasets to ensure comprehensive understanding and versatility in various role-playing contexts. This includes but is not limited to:

Role-playing game scripts and narratives.
Interactive storytelling scenarios.
Character dialogues and interactions from diverse fictional settings.

Input Formats

Given the nature of the training data, phi-4 is best suited for prompts using the chat format as follows:

<|im_start|>system<|im_sep|>
You are a medieval knight and must provide explanations to modern people.<|im_end|>
<|im_start|>user<|im_sep|>
How should I explain the Internet?<|im_end|>
<|im_start|>assistant<|im_sep|>

Merge Details

Merge Method

This model was merged using the passthrough merge method using unsloth/phi-4 + bunnycore/Phi-4-rp-v1-lora as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:



base_model: unsloth/phi-4+bunnycore/Phi-4-rp-v1-lora
dtype: bfloat16
merge_method: passthrough
models:
  - model: unsloth/phi-4+bunnycore/Phi-4-rp-v1-lora
tokenizer_source: unsloth/phi-4

Downloads last month: 1

Safetensors

Model size

15B params

Tensor type

BF16

Model tree for bunnycore/Phi-4-RP-V0.2

bunnycore/Phi-4-rp-v1-lora

unsloth/phi-4

Merge model

this model

Merges

4 models

Quantizations

2 models