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

Libraries

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

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

pipe = pipeline("text-generation", model="SJTU-DENG-Lab/MBD-Math-LLaDA2-mini-DMax-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-Math-LLaDA2-mini-DMax-16B", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

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

Use Docker

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

SGLang

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

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

Add model card metadata, project links, and model description

by nielsr HF Staff - opened about 18 hours ago

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+34

-1

nielsr

about 18 hours ago

Hello!

As part of the Hugging Face community science team, I've opened this PR to enhance your repository's model card. This update includes:

Relevant metadata tags (pipeline_tag: text-generation, library_name: transformers, and license: mit) to make the model more discoverable.
Links to the official GitHub repository, the project page, and the paper.
A concise description of the Multi-Block Diffusion Language Models (MBD-LMs) and the MultiTF training method.
A citation block for researchers who wish to use your work.

Please review the changes and let me know if you have any questions!

Add model card metadata, project links, and model descriptionc8d67632

DrewJin0827

DENG Lab @ SJTU org about 12 hours ago

Thx for helping

DrewJin0827 changed pull request status to merged about 12 hours ago

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