Instructions to use Qwen/Qwen2-0.5B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Qwen/Qwen2-0.5B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="Qwen/Qwen2-0.5B-Instruct", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2-0.5B-Instruct")
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2-0.5B-Instruct", 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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Qwen/Qwen2-0.5B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Qwen/Qwen2-0.5B-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Qwen/Qwen2-0.5B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Qwen/Qwen2-0.5B-Instruct

SGLang

How to use Qwen/Qwen2-0.5B-Instruct 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 "Qwen/Qwen2-0.5B-Instruct" \
    --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": "Qwen/Qwen2-0.5B-Instruct",
		"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 "Qwen/Qwen2-0.5B-Instruct" \
        --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": "Qwen/Qwen2-0.5B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Qwen/Qwen2-0.5B-Instruct with Docker Model Runner:
```
docker model run hf.co/Qwen/Qwen2-0.5B-Instruct
```

Unable to implement onnxruntime_genai in Android project

by davesoma - opened Aug 17, 2024

Discussion

davesoma

Aug 17, 2024

Environment

Android Studio
Gradle
Target SDK: 34
Min SDK: 28

Issue

Failed to resolve: com.microsoft.onnxruntime:onnxruntime_genai-android:latest.release

Working Configuration

implementation 'com.microsoft.onnxruntime:onnxruntime-android:latest.release'

This imports correctly.

Attempted for GenAI

implementation 'com.microsoft.onnxruntime:onnxruntime-genai:0.3.0'

This fails to resolve.

jklj077

Qwen org Aug 19, 2024

Hi, the following is what I found:

Based on information here, version 0.3.0 does not support Android or Qwen.
Based on information here, the main branch supports Android but Requires build from source and Qwen is supported. But I cannot find build instructions for Andorid on its website.
We currently do not provide ONNX weights. You will need to export the weight on your own.

Since I'm not very familiar with these issues, I would suggest seeking advice from the ONNX Runtime GenAI team, as I don't think there is much that we can do to resolve them.

davesoma

Aug 20, 2024

Ok, thank so much!

shoxik

Aug 29, 2024

you have to update to higher version, once you convert don' forget to update version of lib in android app as well.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment