Instructions to use OpenGVLab/SDLM-32B-D4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OpenGVLab/SDLM-32B-D4 with Transformers:

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

pipe = pipeline("text-generation", model="OpenGVLab/SDLM-32B-D4", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("OpenGVLab/SDLM-32B-D4", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("OpenGVLab/SDLM-32B-D4", trust_remote_code=True)
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use OpenGVLab/SDLM-32B-D4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OpenGVLab/SDLM-32B-D4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OpenGVLab/SDLM-32B-D4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/OpenGVLab/SDLM-32B-D4

SGLang

How to use OpenGVLab/SDLM-32B-D4 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 "OpenGVLab/SDLM-32B-D4" \
    --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": "OpenGVLab/SDLM-32B-D4",
		"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 "OpenGVLab/SDLM-32B-D4" \
        --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": "OpenGVLab/SDLM-32B-D4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use OpenGVLab/SDLM-32B-D4 with Docker Model Runner:
```
docker model run hf.co/OpenGVLab/SDLM-32B-D4
```

Enhance model card: Add project page link, overall concept, training, evaluation, case, and acknowledgment sections

by nielsr HF Staff - opened Oct 1, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+180

-84

nielsr

Oct 1, 2025

This PR significantly enhances the model card for SDLM-32B-D4 by integrating comprehensive information from the project's GitHub README. Key improvements include:

Header Links:
- Added a direct link to the project's blog page (🚀 Project Page) for improved discoverability.
- Clarified the existing Hugging Face collection link as 🤗 HuggingFace Collection.
- The arXiv link for the paper is retained as per instructions.
Overall Concept: Added a visual explanation of SDLM's core concept, sourced from the GitHub README's introduction.
Training Section: Included detailed training instructions, environment setup, dependencies, a table of datasets used with their Hugging Face links, training parameters, and loss plots, greatly aiding reproducibility.
Evaluation Section: Added information on the evaluation framework used.
Case Section: Incorporated a visual demonstration of the model's capabilities.
Acknowledgment Section: Added a section to acknowledge foundational contributions, fostering community recognition.

All new content, including images and internal links, has been carefully sourced and adapted from the official GitHub repository to maintain accuracy and consistency.

Enhance model card: Add project page link, overall concept, training, evaluation, case, and acknowledgment sections17d4f541

lll2343 changed pull request status to merged Oct 3, 2025

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