Instructions to use SJTU-DENG-Lab/MBD-Code-LLaDA2-mini-16B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SJTU-DENG-Lab/MBD-Code-LLaDA2-mini-16B with Transformers:

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

pipe = pipeline("text-generation", model="SJTU-DENG-Lab/MBD-Code-LLaDA2-mini-16B", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("SJTU-DENG-Lab/MBD-Code-LLaDA2-mini-16B", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use SJTU-DENG-Lab/MBD-Code-LLaDA2-mini-16B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SJTU-DENG-Lab/MBD-Code-LLaDA2-mini-16B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SJTU-DENG-Lab/MBD-Code-LLaDA2-mini-16B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SJTU-DENG-Lab/MBD-Code-LLaDA2-mini-16B

SGLang

How to use SJTU-DENG-Lab/MBD-Code-LLaDA2-mini-16B 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 "SJTU-DENG-Lab/MBD-Code-LLaDA2-mini-16B" \
    --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": "SJTU-DENG-Lab/MBD-Code-LLaDA2-mini-16B",
		"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 "SJTU-DENG-Lab/MBD-Code-LLaDA2-mini-16B" \
        --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": "SJTU-DENG-Lab/MBD-Code-LLaDA2-mini-16B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use SJTU-DENG-Lab/MBD-Code-LLaDA2-mini-16B with Docker Model Runner:
```
docker model run hf.co/SJTU-DENG-Lab/MBD-Code-LLaDA2-mini-16B
```

nielsr HF Staff commited on Jul 5

Commit

7632464

verified ·

1 Parent(s): 4b11eee

Add model card metadata, links and citation

Browse files

Hi! I'm Niels from the Hugging Face team.

I noticed this model repository is missing metadata and a complete model card. This PR aims to improve the model's discoverability and documentation on the Hugging Face Hub by:
- Adding YAML metadata including `pipeline_tag: text-generation`, `library_name: transformers`, and `license: mit`.
- Documenting the model with references and links to the paper, project page, and official GitHub repository.
- Adding a BibTeX citation for the paper so users can easily cite your work.

Please let me know if you have any feedback or would like to make changes.

Files changed (1) hide show

README.md +32 -1

README.md CHANGED Viewed

	@@ -1 +1,32 @@
1	- ~~Model weight of [MBD~~-~~LMs](https://arxiv.org/abs/2606.29215)~~

+---
+license: mit
+library_name: transformers
+pipeline_tag: text-generation
+---
+# Multi-Block Diffusion Language Models (MBD-LMs)
+This repository contains the model weights for **MBD-LMs**, presented in the paper [Multi-Block Diffusion Language Models](https://arxiv.org/abs/2606.29215).
+- **Project Page:** [SJTU-DENG-Lab Project Page](https://sjtu-deng-lab.github.io/mbd-lms)
+- **GitHub Repository:** [SJTU-DENG-Lab/mbd-lms](https://github.com/SJTU-DENG-Lab/mbd-lms)
+- **Inference Engine (Diffulex):** [SJTU-DENG-Lab/Diffulex](https://github.com/SJTU-DENG-Lab/Diffulex)
+## Introduction
+Block Diffusion Language Models (BD-LMs) improve diffusion-based text generation with KV caching and flexible-length generation. Multi-Block Diffusion Language Models (MBD-LMs) extend this paradigm to **Multi-Block Diffusion (MultiBD)**, where a running-set of consecutive blocks is decoded concurrently for inter-block parallelism.
+This model is obtained by post-training BD-LMs with Multi-block Teacher Forcing (MultiTF), which integrates teacher forcing and diffusion forcing by training on bounded noise-groups conditioned on clean prefixes.
+## Citation
+If you find this work useful, please consider citing the paper:
+```bibtex
+@article{jin2026multiblock,
+  title={Multi-Block Diffusion Language Models},
+  author={Jin, Yijie and Xu, Jiajun and Liu, Yuxuan and Xu, Chenkai and Tu, Yi and Li, Jiajun and Tu, Dandan and Yan, Xiaohui and Yu, Kai and Liu, Pengfei and Deng, Zhijie},
+  journal={arXiv preprint arXiv:2606.29215},
+  year={2026}
+}
+```