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

Libraries

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

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

pipe = pipeline("text-generation", model="EmbeddedLLM/Phi-3-medium-4k-instruct-onnx-directml", 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("EmbeddedLLM/Phi-3-medium-4k-instruct-onnx-directml", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("EmbeddedLLM/Phi-3-medium-4k-instruct-onnx-directml", 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 EmbeddedLLM/Phi-3-medium-4k-instruct-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-medium-4k-instruct-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-medium-4k-instruct-onnx-directml",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

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

SGLang

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

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

ssyok commited on Jul 19, 2024

Commit

88e66ea

verified ·

1 Parent(s): 1fe23a1

Update README.md

Browse files

Files changed (1) hide show

README.md +41 -3

README.md CHANGED Viewed

@@ -1,3 +1,41 @@
----
-license: mit
----

+---
+license: mit
+pipeline_tag: text-generation
+tags:
+ - ONNX
+ - DML
+ - ONNXRuntime
+ - phi3
+ - nlp
+ - conversational
+ - custom_code
+inference: false
+language:
+- en
+---
+# EmbeddedLLM/Phi-3-medium-4k-instruct-onnx-directml
+## Performance Metrics
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+### 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 | -  |