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
```

lll2343 commited on Oct 3, 2025

Commit

ec105fd

verified ·

1 Parent(s): 71164b1

Update README.md

Browse files

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -194,7 +194,7 @@ Trade-off between performance and speed under different confidence thresholds τ
     Our training setting is:
     <p align="center">
-        <img src="https://huggingface.co/OpenGVLab/SDLM-32B-D4/resolve/main/assets/hyper-param.png" width="50%"></a>
     </p>
     The training loss of our 3B model. loss_pos_`i` refers to the loss at the `i`-th position of each block. The loss at `i=0` is close to the SFT loss of AR's NTP.
@@ -214,7 +214,7 @@ Trade-off between performance and speed under different confidence thresholds τ
     | :-- | :-- | :-- | :-- | :-- | :-- | :-- | :-- |
     | loss_pos_1 | loss_pos_2 | loss_pos_3 | loss_pos_4 | -- | -- | -- | -- |
-    ![](https://huggingface.co/OpenGVLab/SDLM-32B-D4/resolve/main/assets/train_log_3b.png)
 ## Evaluation
@@ -223,7 +223,7 @@ Currently, we use [Opencompass](https://github.com/open-compass/opencompass) for
 ## Case
 <p align="center">
-    <img src="https://huggingface.co/OpenGVLab/SDLM-32B-D4/resolve/main/assets/case.gif" width="70%"></a>
 </p>
 ## Acknowledge

     Our training setting is:
     <p align="center">
+        <img src="https://github.com/OpenGVLab/SDLM/blob/main/assets/hyper-param.png" width="50%"></a>
     </p>
     The training loss of our 3B model. loss_pos_`i` refers to the loss at the `i`-th position of each block. The loss at `i=0` is close to the SFT loss of AR's NTP.
     | :-- | :-- | :-- | :-- | :-- | :-- | :-- | :-- |
     | loss_pos_1 | loss_pos_2 | loss_pos_3 | loss_pos_4 | -- | -- | -- | -- |
+    ![](https://github.com/OpenGVLab/SDLM/blob/main/assets/train_log_3b.png)
 ## Evaluation
 ## Case
 <p align="center">
+    <img src="https://github.com/OpenGVLab/SDLM/blob/main/assets/case.gif" width="70%"></a>
 </p>
 ## Acknowledge