Instructions to use EmbeddedLLM/Phi-3-mini-4k-instruct-062024-int4-onnx-directml with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use EmbeddedLLM/Phi-3-mini-4k-instruct-062024-int4-onnx-directml with Transformers:

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

pipe = pipeline("text-generation", model="EmbeddedLLM/Phi-3-mini-4k-instruct-062024-int4-onnx-directml", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("EmbeddedLLM/Phi-3-mini-4k-instruct-062024-int4-onnx-directml", trust_remote_code=True)
model = AutoModelForMultimodalLM.from_pretrained("EmbeddedLLM/Phi-3-mini-4k-instruct-062024-int4-onnx-directml", trust_remote_code=True)
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 EmbeddedLLM/Phi-3-mini-4k-instruct-062024-int4-onnx-directml with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "EmbeddedLLM/Phi-3-mini-4k-instruct-062024-int4-onnx-directml"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "EmbeddedLLM/Phi-3-mini-4k-instruct-062024-int4-onnx-directml",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/EmbeddedLLM/Phi-3-mini-4k-instruct-062024-int4-onnx-directml

SGLang

How to use EmbeddedLLM/Phi-3-mini-4k-instruct-062024-int4-onnx-directml 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 "EmbeddedLLM/Phi-3-mini-4k-instruct-062024-int4-onnx-directml" \
    --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": "EmbeddedLLM/Phi-3-mini-4k-instruct-062024-int4-onnx-directml",
		"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 "EmbeddedLLM/Phi-3-mini-4k-instruct-062024-int4-onnx-directml" \
        --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": "EmbeddedLLM/Phi-3-mini-4k-instruct-062024-int4-onnx-directml",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use EmbeddedLLM/Phi-3-mini-4k-instruct-062024-int4-onnx-directml with Docker Model Runner:
```
docker model run hf.co/EmbeddedLLM/Phi-3-mini-4k-instruct-062024-int4-onnx-directml
```

EmbeddedLLM/Phi-3-mini-4k-instruct-062024-int4-onnx-directml

Model Summary

This model is an ONNX-optimized version of microsoft/Phi-3-mini-4k-instruct (June 2024), designed to provide accelerated inference on a variety of hardware using ONNX Runtime(CPU and DirectML). DirectML is a high-performance, hardware-accelerated DirectX 12 library for machine learning, providing GPU acceleration for a wide range of supported hardware and drivers, including AMD, Intel, NVIDIA, and Qualcomm GPUs.

ONNX Models

Here are some of the optimized configurations we have added:

ONNX model for int4 DirectML: ONNX model for AMD, Intel, and NVIDIA GPUs on Windows, quantized to int4 using AWQ.

Hardware Requirements

Minimum Configuration:

Windows: DirectX 12-capable GPU (AMD/Nvidia)
CPU: x86_64 / ARM64 Tested Configurations:
GPU: AMD Ryzen 8000 Series iGPU (DirectML)
CPU: AMD Ryzen CPU

Model Description

Developed by: Microsoft
Model type: ONNX
Language(s) (NLP): Python, C, C++
License: Apache License Version 2.0
Model Description: This model is a conversion of the Phi-3-mini-4k-instruct-062024 for ONNX Runtime inference, optimized for DirectML.

Performance Metrics

DirectML

We measured the performance of DirectML on AMD Ryzen 9 7940HS /w Radeon 78

Prompt Length	Generation Length	Average Throughput (tps)
128	128	-
128	256	-
128	512	-
128	1024	-
256	128	-
256	256	-
256	512	-
256	1024	-
512	128	-
512	256	-
512	512	-
512	1024	-
1024	128	-
1024	256	-
1024	512	-
1024	1024	-

Downloads last month: 6

Collection including EmbeddedLLM/Phi-3-mini-4k-instruct-062024-int4-onnx-directml

Onnxruntime DirectML GenAI

Collection

Model Powered by Onnxruntime DirectML GenAI • 12 items • Updated Aug 6, 2024 • 1