Instructions to use OpenGVLab/SDLM-3B-D4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OpenGVLab/SDLM-3B-D4 with Transformers:

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

pipe = pipeline("text-generation", model="OpenGVLab/SDLM-3B-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-3B-D4", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("OpenGVLab/SDLM-3B-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-3B-D4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OpenGVLab/SDLM-3B-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-3B-D4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/OpenGVLab/SDLM-3B-D4

SGLang

How to use OpenGVLab/SDLM-3B-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-3B-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-3B-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-3B-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-3B-D4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use OpenGVLab/SDLM-3B-D4 with Docker Model Runner:
```
docker model run hf.co/OpenGVLab/SDLM-3B-D4
```

lll2343 commited on Sep 29, 2025

Commit

a1656f9

verified ·

1 Parent(s): b9b5ece

Upload config.json with huggingface_hub

Browse files

Files changed (1) hide show

config.json +37 -0

config.json ADDED Viewed

	@@ -0,0 +1,37 @@

+{
+  "architectures": [
+    "SDLMQwen2ForCausalLM"
+  ],
+  "auto_map": {
+    "AutoConfig": "configuration_sdlm.SDLMQwen2Config",
+    "AutoModelForCausalLM": "modeling_sdlm.SDLMQwen2ForCausalLM"
+  },
+  "attention_dropout": 0.0,
+  "attn_implementation": "eager",
+  "block_size": 4,
+  "bos_token_id": 151643,
+  "casual_attn": false,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 36,
+  "model_type": "qwen2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "text_mask_token": "<text_mask>",
+  "text_mask_token_id": 151665,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.2",
+  "use_cache": true,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151666
+}