Instructions to use TitleOS/HomePhi4_4B_FP16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TitleOS/HomePhi4_4B_FP16 with Transformers:

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

pipe = pipeline("text-generation", model="TitleOS/HomePhi4_4B_FP16")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TitleOS/HomePhi4_4B_FP16")
model = AutoModelForCausalLM.from_pretrained("TitleOS/HomePhi4_4B_FP16")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use TitleOS/HomePhi4_4B_FP16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TitleOS/HomePhi4_4B_FP16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TitleOS/HomePhi4_4B_FP16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/TitleOS/HomePhi4_4B_FP16

SGLang

How to use TitleOS/HomePhi4_4B_FP16 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 "TitleOS/HomePhi4_4B_FP16" \
    --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": "TitleOS/HomePhi4_4B_FP16",
		"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 "TitleOS/HomePhi4_4B_FP16" \
        --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": "TitleOS/HomePhi4_4B_FP16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use TitleOS/HomePhi4_4B_FP16 with Docker Model Runner:
```
docker model run hf.co/TitleOS/HomePhi4_4B_FP16
```

TitleOS commited on Dec 6, 2025

Commit

22aa16d

verified ·

1 Parent(s): f68ed19

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -20,7 +20,7 @@ pipeline_tag: text-generation
 ![Model Icon](https://img.shields.io/badge/Home%20Assistant-Compatible-41BDF5) ![Phi-4](https://img.shields.io/badge/Base-Phi%204%20Mini-blue)
-**HomePhi4_4B-FP16** is a fine-tuned version of Microsoft's [Phi-4 Mini](https://huggingface.co/microsoft/Phi-4-mini-instruct) (3.8B parameters), specifically optimized for controlling **Home Assistant** instances via natural language. The Lora adapter was then merged against the original FP16 model to create this instance.
 It has been fine-tuned on the [acon96/Home-Assistant-Requests](https://huggingface.co/datasets/acon96/Home-Assistant-Requests) dataset to excel at interpreting user intent and generating accurate JSON function calls to control smart home devices (lights, fans, switches, etc.). This model is designed to be small enough to run locally on edge hardware (like an N100 or Raspberry Pi 5 with 8GB RAM) while maintaining high reasoning capabilities.

 ![Model Icon](https://img.shields.io/badge/Home%20Assistant-Compatible-41BDF5) ![Phi-4](https://img.shields.io/badge/Base-Phi%204%20Mini-blue)
+**HomePhi4_4B-FP16** is a fine-tuned version of Microsoft's [Phi-4 Mini Reasoning](microsoft/Phi-4-mini-reasoning) (3.8B parameters), specifically optimized for controlling **Home Assistant** instances via natural language. The Lora adapter was then merged against the original FP16 model to create this instance.
 It has been fine-tuned on the [acon96/Home-Assistant-Requests](https://huggingface.co/datasets/acon96/Home-Assistant-Requests) dataset to excel at interpreting user intent and generating accurate JSON function calls to control smart home devices (lights, fans, switches, etc.). This model is designed to be small enough to run locally on edge hardware (like an N100 or Raspberry Pi 5 with 8GB RAM) while maintaining high reasoning capabilities.