Instructions to use Qwen/Qwen2-Math-72B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Qwen/Qwen2-Math-72B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="Qwen/Qwen2-Math-72B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2-Math-72B-Instruct")
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2-Math-72B-Instruct")
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

vLLM

How to use Qwen/Qwen2-Math-72B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Qwen/Qwen2-Math-72B-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-Math-72B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Qwen/Qwen2-Math-72B-Instruct

SGLang

How to use Qwen/Qwen2-Math-72B-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-Math-72B-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-Math-72B-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-Math-72B-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-Math-72B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Qwen/Qwen2-Math-72B-Instruct with Docker Model Runner:
```
docker model run hf.co/Qwen/Qwen2-Math-72B-Instruct
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Qwen2-Math-72B-Instruct

🚨 Temporarily this model mainly supports English. We will release bilingual (English & Chinese) models soon!

Introduction

Over the past year, we have dedicated significant effort to researching and enhancing the reasoning capabilities of large language models, with a particular focus on their ability to solve arithmetic and mathematical problems. Today, we are delighted to introduce a serise of math-specific large language models of our Qwen2 series, Qwen2-Math and Qwen2-Math-Instruct-1.5B/7B/72B. Qwen2-Math is a series of specialized math language models built upon the Qwen2 LLMs, which significantly outperforms the mathematical capabilities of open-source models and even closed-source models (e.g., GPT4o). We hope that Qwen2-Math can contribute to the scientific community for solving advanced mathematical problems that require complex, multi-step logical reasoning.

Model Details

For more details, please refer to our blog post and GitHub repo.

Requirements

transformers>=4.40.0 for Qwen2-Math models. The latest version is recommended.

🚨 This is a must because `transformers` integrated Qwen2 codes since `4.37.0`.

For requirements on GPU memory and the respective throughput, see similar results of Qwen2 here.

Quick Start

Qwen2-Math-72B-Instruct is an instruction model for chatting;

Qwen2-Math-72B is a base model typically used for completion and few-shot inference, serving as a better starting point for fine-tuning.

🤗 Hugging Face Transformers

Qwen2-Math can be deployed and infered in the same way as Qwen2. Here we show a code snippet to show you how to use the chat model with transformers:

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "Qwen/Qwen2-Math-72B-Instruct"
device = "cuda" # the device to load the model onto

model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "Find the value of $x$ that satisfies the equation $4x+5 = 6x+7$."
messages = [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=512
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]

🤖 ModelScope

We strongly advise users especially those in mainland China to use ModelScope. snapshot_download can help you solve issues concerning downloading checkpoints.

Citation

If you find our work helpful, feel free to give us a citation.

@article{yang2024qwen2,
  title={Qwen2 technical report},
  author={Yang, An and Yang, Baosong and Hui, Binyuan and Zheng, Bo and Yu, Bowen and Zhou, Chang and Li, Chengpeng and Li, Chengyuan and Liu, Dayiheng and Huang, Fei and others},
  journal={arXiv preprint arXiv:2407.10671},
  year={2024}
}