Instructions to use divelab/OPDLM-MATH-4B-Thinking with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use divelab/OPDLM-MATH-4B-Thinking with Transformers:

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

pipe = pipeline("text-generation", model="divelab/OPDLM-MATH-4B-Thinking")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelWithLMHead
model = AutoModelWithLMHead.from_pretrained("divelab/OPDLM-MATH-4B-Thinking", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use divelab/OPDLM-MATH-4B-Thinking with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "divelab/OPDLM-MATH-4B-Thinking"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "divelab/OPDLM-MATH-4B-Thinking",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/divelab/OPDLM-MATH-4B-Thinking

SGLang

How to use divelab/OPDLM-MATH-4B-Thinking 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 "divelab/OPDLM-MATH-4B-Thinking" \
    --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": "divelab/OPDLM-MATH-4B-Thinking",
		"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 "divelab/OPDLM-MATH-4B-Thinking" \
        --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": "divelab/OPDLM-MATH-4B-Thinking",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use divelab/OPDLM-MATH-4B-Thinking with Docker Model Runner:
```
docker model run hf.co/divelab/OPDLM-MATH-4B-Thinking
```

OPDLM-MATH-4B-Thinking

OPDLM-MATH-4B-Thinking is an On-Policy Distillation Language Model (OPDLM) — a block-diffusion language model (block size 4, 4 denoising steps per block) post-trained for mathematical reasoning. It is built on a block-diffusion adaptation of Qwen/Qwen3-4B (architecture a2d-qwen3).

This is the thinking variant: long-context (8k) math post-training with an explicit chain-of-thought thinking block enabled at inference.

arXiv report: arxiv.org/abs/2606.06712

Usage

This model uses custom modeling code; load with trust_remote_code=True. Generation is block-diffusion (non–left-to-right), so use the project's inference utilities (block_size=4, denoising_steps_per_block=4) rather than vanilla model.generate.

from transformers import AutoModel, AutoTokenizer
tok = AutoTokenizer.from_pretrained("divelab/OPDLM-MATH-4B-Thinking", trust_remote_code=True)
model = AutoModel.from_pretrained("divelab/OPDLM-MATH-4B-Thinking", trust_remote_code=True)