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

Libraries

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

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

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

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

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

Use Docker

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

SGLang

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

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

OPDLM-MATH-4B / README.md

shubhamprshr

Update README.md

1e12a2c verified 21 days ago

preview code

Raw

History Blame Contribute Delete

1.19 kB

	---
	license: apache-2.0
	library_name: transformers
	pipeline_tag: text-generation
	tags:
	- opdlm
	- block-diffusion
	- diffusion-language-model
	- math
	- qwen3
	base_model: Qwen/Qwen3-4B
	---

	# OPDLM-MATH-4B

	OPDLM-MATH-4B 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 base (non-thinking) variant: short-context (2k) math post-training, no explicit chain-of-thought thinking block. ArXiv report: arxiv.org/abs/2606.06712

	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`.

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