Instructions to use LocalAI-io/LocalAI-functioncall-phi-4-v0.3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LocalAI-io/LocalAI-functioncall-phi-4-v0.3 with Transformers:

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

pipe = pipeline("text-generation", model="LocalAI-io/LocalAI-functioncall-phi-4-v0.3")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("LocalAI-io/LocalAI-functioncall-phi-4-v0.3")
model = AutoModelForCausalLM.from_pretrained("LocalAI-io/LocalAI-functioncall-phi-4-v0.3")
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 LocalAI-io/LocalAI-functioncall-phi-4-v0.3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LocalAI-io/LocalAI-functioncall-phi-4-v0.3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LocalAI-io/LocalAI-functioncall-phi-4-v0.3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/LocalAI-io/LocalAI-functioncall-phi-4-v0.3

SGLang

How to use LocalAI-io/LocalAI-functioncall-phi-4-v0.3 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 "LocalAI-io/LocalAI-functioncall-phi-4-v0.3" \
    --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": "LocalAI-io/LocalAI-functioncall-phi-4-v0.3",
		"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 "LocalAI-io/LocalAI-functioncall-phi-4-v0.3" \
        --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": "LocalAI-io/LocalAI-functioncall-phi-4-v0.3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio new

How to use LocalAI-io/LocalAI-functioncall-phi-4-v0.3 with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for LocalAI-io/LocalAI-functioncall-phi-4-v0.3 to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for LocalAI-io/LocalAI-functioncall-phi-4-v0.3 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for LocalAI-io/LocalAI-functioncall-phi-4-v0.3 to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="LocalAI-io/LocalAI-functioncall-phi-4-v0.3",
    max_seq_length=2048,
)

Docker Model Runner
How to use LocalAI-io/LocalAI-functioncall-phi-4-v0.3 with Docker Model Runner:
```
docker model run hf.co/LocalAI-io/LocalAI-functioncall-phi-4-v0.3
```

LocalAI-functioncall-phi-4-v0.3

File size: 1,445 Bytes

503ea80
 
 
 
 
 
 
 
eb7c1ae
503ea80
 
 
afd8a69
 
 
 
 
a63ad38
503ea80
 
afd8a69
503ea80
 
afd8a69
503ea80
7f32be7
 
0ed990a
 
 
3a802ae
0ed990a
7f32be7
 
 
 
 
 
 
afd8a69
de513ad
 
 
afd8a69

---
base_model: unsloth/phi-4-unsloth-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
- sft
license: apache-2.0
language:
- en
datasets:
- mudler/glaive-unsloth-localai
- mudler/o1-unsloth
- mudler/open-o1-sft-unsloth
- mlabonne/FineTome-100k

---

<img src="https://cdn-uploads.huggingface.co/production/uploads/647374aa7ff32a81ac6d35d4/Dzbdzn27KEc3K6zNNi070.png" style="display: block;margin-left: auto;margin-right: auto;width: 50%;">


## Description

A model tailored to be conversational and execute function calls with [LocalAI](https://github.com/mudler/LocalAI). This model is based on phi-4.

- llama3.2-1b version: https://huggingface.co/mudler/LocalAI-functioncall-llama3.2-1b-v0.4
- llama3.2-3b version: https://huggingface.co/mudler/LocalAI-functioncall-llama3.2-3b-v0.5
- phi-4 version: https://huggingface.co/mudler/LocalAI-functioncall-phi-4-v0.3
- qwen2.5 (7b) version: https://huggingface.co/mudler/LocalAI-functioncall-qwen2.5-7b-v0.5

## How to run

With LocalAI:

```
local-ai run LocalAI-functioncall-phi-4-v0.3
```

[![local-ai-banner.png](https://cdn-uploads.huggingface.co/production/uploads/647374aa7ff32a81ac6d35d4/bXvNcxQqQ-wNAnISmx3PS.png)](https://localai.io)


## Updates

This is the third iteration of `https://huggingface.co/mudler/LocalAI-functioncall-phi-4-v0.1` with improved o1 capabilities from the [Open-o1](https://huggingface.co/datasets/O1-OPEN/OpenO1-SFT) dataset.