Instructions to use OpenVINO/Phi-3-mini-4k-instruct-int8-ov with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OpenVINO/Phi-3-mini-4k-instruct-int8-ov with Transformers:

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

pipe = pipeline("text-generation", model="OpenVINO/Phi-3-mini-4k-instruct-int8-ov", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("OpenVINO/Phi-3-mini-4k-instruct-int8-ov", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("OpenVINO/Phi-3-mini-4k-instruct-int8-ov", trust_remote_code=True, device_map="auto")
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 Settings

vLLM

How to use OpenVINO/Phi-3-mini-4k-instruct-int8-ov with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OpenVINO/Phi-3-mini-4k-instruct-int8-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-3-mini-4k-instruct-int8-ov",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/OpenVINO/Phi-3-mini-4k-instruct-int8-ov

SGLang

How to use OpenVINO/Phi-3-mini-4k-instruct-int8-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-3-mini-4k-instruct-int8-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-3-mini-4k-instruct-int8-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-3-mini-4k-instruct-int8-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-3-mini-4k-instruct-int8-ov",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use OpenVINO/Phi-3-mini-4k-instruct-int8-ov with Docker Model Runner:
```
docker model run hf.co/OpenVINO/Phi-3-mini-4k-instruct-int8-ov
```

Phi-3-mini-4k-instruct-int8-ov / README.md

sylwia-kuros

Update README.md

8141b65 verified almost 2 years ago

preview code

Raw

History Blame Contribute Delete

2.83 kB

	---
	license: mit
	license_link: https://choosealicense.com/licenses/mit/
	base_model:
	- microsoft/Phi-3-mini-4k-instruct
	base_model_relation: quantized
	---
	# Phi-3-mini-4k-instruct-int8-ov
	* Model creator: [Microsoft](https://huggingface.co/microsoft)
	* Original model: [Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct)

	## Description
	This is [Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct) model converted to the [OpenVINO™ IR](https://docs.openvino.ai/2024/documentation/openvino-ir-format.html) (Intermediate Representation) format with weights compressed to INT8 by [NNCF](https://github.com/openvinotoolkit/nncf).

	## Quantization Parameters

	Weight compression was performed using `nncf.compress_weights` with the following parameters:

	* mode: int8_asym
	* ratio: 1

	For more information on quantization, check the [OpenVINO model optimization guide](https://docs.openvino.ai/2024/openvino-workflow/model-optimization-guide/weight-compression.html).


	## Compatibility

	The provided OpenVINO™ IR model is compatible with:

	* OpenVINO version 2024.4.0 and higher
	* Optimum Intel 1.23.1 and higher

	## Running Model Inference

	1. Install packages required for using [Optimum Intel](https://huggingface.co/docs/optimum/intel/index) integration with the OpenVINO backend:

	```
	pip install optimum[openvino]
	```

	2. Run model inference:

	```
	from transformers import AutoTokenizer
	from optimum.intel.openvino import OVModelForCausalLM

	model_id = "OpenVINO/Phi-3-mini-4k-instruct-int8-ov"
	tokenizer = AutoTokenizer.from_pretrained(model_id)
	model = OVModelForCausalLM.from_pretrained(model_id)

	inputs = tokenizer("What is OpenVINO?", return_tensors="pt")

	outputs = model.generate(**inputs, max_length=200)
	text = tokenizer.batch_decode(outputs)[0]
	print(text)
	```

	For more examples and possible optimizations, refer to the [OpenVINO Large Language Model Inference Guide](https://docs.openvino.ai/2024/learn-openvino/llm_inference_guide.html).

	## Limitations

	Check the original model card for [original model card](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct) for limitations.

	## Legal information

	The original model is distributed under [mit](https://choosealicense.com/licenses/mit/) license. More details can be found in [original model card](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct).

	## Disclaimer

	Intel is committed to respecting human rights and avoiding causing or contributing to adverse impacts on human rights. See [Intel’s Global Human Rights Principles](https://www.intel.com/content/dam/www/central-libraries/us/en/documents/policy-human-rights.pdf). Intel’s products and software are intended only to be used in applications that do not cause or contribute to adverse impacts on human rights.