Instructions to use OpenVINO/phi-4-fp16-ov with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OpenVINO/phi-4-fp16-ov with Transformers:

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

pipe = pipeline("text-generation", model="OpenVINO/phi-4-fp16-ov")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("OpenVINO/phi-4-fp16-ov")
model = AutoModelForCausalLM.from_pretrained("OpenVINO/phi-4-fp16-ov")
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 OpenVINO/phi-4-fp16-ov with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OpenVINO/phi-4-fp16-ov"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OpenVINO/phi-4-fp16-ov",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/OpenVINO/phi-4-fp16-ov

SGLang

How to use OpenVINO/phi-4-fp16-ov 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 "OpenVINO/phi-4-fp16-ov" \
    --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": "OpenVINO/phi-4-fp16-ov",
		"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 "OpenVINO/phi-4-fp16-ov" \
        --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": "OpenVINO/phi-4-fp16-ov",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use OpenVINO/phi-4-fp16-ov with Docker Model Runner:
```
docker model run hf.co/OpenVINO/phi-4-fp16-ov
```

phi-4-fp16-ov / openvino_detokenizer.xml

openvino-ci

Upload folder using huggingface_hub

5f3a2e7 verified about 1 year ago

raw

history blame contribute delete

7.01 kB

	<?xml version="1.0"?>
	<net name="detokenizer" version="11">
	<layers>
	<layer id="0" name="Parameter_212474" type="Parameter" version="opset1">
	<data shape="?,?" element_type="i64" />
	<output>
	<port id="0" precision="I64" names="Parameter_212474">
	<dim>-1</dim>
	<dim>-1</dim>
	</port>
	</output>
	</layer>
	<layer id="1" name="Convert_212644" type="Convert" version="opset1">
	<data destination_type="i32" />
	<input>
	<port id="0" precision="I64">
	<dim>-1</dim>
	<dim>-1</dim>
	</port>
	</input>
	<output>
	<port id="1" precision="I32">
	<dim>-1</dim>
	<dim>-1</dim>
	</port>
	</output>
	</layer>
	<layer id="2" name="Constant_212476" type="Const" version="opset1">
	<data element_type="i32" shape="100352" offset="0" size="401408" />
	<output>
	<port id="0" precision="I32">
	<dim>100352</dim>
	</port>
	</output>
	</layer>
	<layer id="3" name="Constant_212478" type="Const" version="opset1">
	<data element_type="i32" shape="100352" offset="401408" size="401408" />
	<output>
	<port id="0" precision="I32">
	<dim>100352</dim>
	</port>
	</output>
	</layer>
	<layer id="4" name="Constant_212480" type="Const" version="opset1">
	<data element_type="u8" shape="644978" offset="802816" size="644978" />
	<output>
	<port id="0" precision="U8">
	<dim>644978</dim>
	</port>
	</output>
	</layer>
	<layer id="5" name="Slice_212485" type="Const" version="opset1">
	<data element_type="i32" shape="96" offset="1447794" size="384" />
	<output>
	<port id="0" precision="I32">
	<dim>96</dim>
	</port>
	</output>
	</layer>
	<layer id="6" name="VocabDecoder_212487" type="VocabDecoder" version="extension">
	<data skip_tokens="" />
	<input>
	<port id="0" precision="I32">
	<dim>-1</dim>
	<dim>-1</dim>
	</port>
	<port id="1" precision="I32">
	<dim>100352</dim>
	</port>
	<port id="2" precision="I32">
	<dim>100352</dim>
	</port>
	<port id="3" precision="U8">
	<dim>644978</dim>
	</port>
	<port id="4" precision="I32">
	<dim>96</dim>
	</port>
	</input>
	<output>
	<port id="5" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="6" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="7" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="8" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="9" precision="U8">
	<dim>-1</dim>
	</port>
	</output>
	</layer>
	<layer id="7" name="FuzeRagged_212488" type="FuzeRagged" version="extension">
	<input>
	<port id="0" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="1" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="2" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="3" precision="I32">
	<dim>-1</dim>
	</port>
	</input>
	<output>
	<port id="4" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="5" precision="I32">
	<dim>-1</dim>
	</port>
	</output>
	</layer>
	<layer id="8" name="UTF8Validate_212489" type="UTF8Validate" version="extension">
	<data replace_mode="true" />
	<input>
	<port id="0" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="1" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="2" precision="U8">
	<dim>-1</dim>
	</port>
	</input>
	<output>
	<port id="3" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="4" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="5" precision="U8">
	<dim>-1</dim>
	</port>
	</output>
	</layer>
	<layer id="9" name="StringTensorPack_212490" type="StringTensorPack" version="opset15">
	<input>
	<port id="0" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="1" precision="I32">
	<dim>-1</dim>
	</port>
	<port id="2" precision="U8">
	<dim>-1</dim>
	</port>
	</input>
	<output>
	<port id="3" precision="STRING" names="Result_212491,string_output">
	<dim>-1</dim>
	</port>
	</output>
	</layer>
	<layer id="10" name="Result_212491" type="Result" version="opset1" output_names="Result_212491,string_output">
	<input>
	<port id="0" precision="STRING">
	<dim>-1</dim>
	</port>
	</input>
	</layer>
	</layers>
	<edges>
	<edge from-layer="0" from-port="0" to-layer="1" to-port="0" />
	<edge from-layer="1" from-port="1" to-layer="6" to-port="0" />
	<edge from-layer="2" from-port="0" to-layer="6" to-port="1" />
	<edge from-layer="3" from-port="0" to-layer="6" to-port="2" />
	<edge from-layer="4" from-port="0" to-layer="6" to-port="3" />
	<edge from-layer="5" from-port="0" to-layer="6" to-port="4" />
	<edge from-layer="6" from-port="7" to-layer="7" to-port="2" />
	<edge from-layer="6" from-port="9" to-layer="8" to-port="2" />
	<edge from-layer="6" from-port="8" to-layer="7" to-port="3" />
	<edge from-layer="6" from-port="6" to-layer="7" to-port="1" />
	<edge from-layer="6" from-port="5" to-layer="7" to-port="0" />
	<edge from-layer="7" from-port="4" to-layer="8" to-port="0" />
	<edge from-layer="7" from-port="5" to-layer="8" to-port="1" />
	<edge from-layer="8" from-port="3" to-layer="9" to-port="0" />
	<edge from-layer="8" from-port="4" to-layer="9" to-port="1" />
	<edge from-layer="8" from-port="5" to-layer="9" to-port="2" />
	<edge from-layer="9" from-port="3" to-layer="10" to-port="0" />
	</edges>
	<rt_info>
	<add_attention_mask value="True" />
	<add_prefix_space />
	<add_special_tokens value="True" />
	<bos_token_id value="100257" />
	<chat_template value="{% for message in messages %}{% if (message['role'] == 'system') %}{{'<\|im_start\|>system<\|im_sep\|>' + message['content'] + '<\|im_end\|>'}}{% elif (message['role'] == 'user') %}{{'<\|im_start\|>user<\|im_sep\|>' + message['content'] + '<\|im_end\|>'}}{% elif (message['role'] == 'assistant') %}{{'<\|im_start\|>assistant<\|im_sep\|>' + message['content'] + '<\|im_end\|>'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<\|im_start\|>assistant<\|im_sep\|>' }}{% endif %}" />
	<clean_up_tokenization_spaces />
	<detokenizer_input_type value="i64" />
	<eos_token_id value="100265" />
	<handle_special_tokens_with_re />
	<max_length />
	<number_of_inputs value="1" />
	<openvino_tokenizers_version value="2025.1.0.0-523-710ddf14de8" />
	<openvino_version value="2025.1.0-18503-6fec06580ab-releases/2025/1" />
	<original_tokenizer_class value="<class 'transformers.models.gpt2.tokenization_gpt2_fast.GPT2TokenizerFast'>" />
	<pad_token_id value="100349" />
	<sentencepiece_version value="0.2.0" />
	<skip_special_tokens value="True" />
	<streaming_detokenizer value="False" />
	<tiktoken_version value="0.9.0" />
	<tokenizer_output_type value="i64" />
	<tokenizers_version value="0.21.1" />
	<transformers_version value="4.51.3" />
	<use_max_padding value="False" />
	<use_sentencepiece_backend value="False" />
	<utf8_replace_mode value="replace" />
	<with_detokenizer value="True" />
	</rt_info>
	</net>