Instructions to use SenseLLM/StructureCoder-1.5B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SenseLLM/StructureCoder-1.5B with Transformers:

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

pipe = pipeline("text-generation", model="SenseLLM/StructureCoder-1.5B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SenseLLM/StructureCoder-1.5B")
model = AutoModelForCausalLM.from_pretrained("SenseLLM/StructureCoder-1.5B")
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 SenseLLM/StructureCoder-1.5B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SenseLLM/StructureCoder-1.5B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SenseLLM/StructureCoder-1.5B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SenseLLM/StructureCoder-1.5B

SGLang

How to use SenseLLM/StructureCoder-1.5B 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 "SenseLLM/StructureCoder-1.5B" \
    --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": "SenseLLM/StructureCoder-1.5B",
		"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 "SenseLLM/StructureCoder-1.5B" \
        --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": "SenseLLM/StructureCoder-1.5B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use SenseLLM/StructureCoder-1.5B with Docker Model Runner:
```
docker model run hf.co/SenseLLM/StructureCoder-1.5B
```

Improve model card: Add pipeline tag and library name

by nielsr HF Staff - opened Sep 1, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

-1

Improve model card: Add pipeline tag and library name4d77618e

nielsr

Sep 1, 2025

This PR enhances the model card for SenseLLM/StructureCoder-7B by:

Adding the pipeline_tag: text-generation, which makes the model discoverable under the text-generation pipeline on the Hugging Face Hub (https://huggingface.co/models?pipeline_tag=text-generation).
Adding the library_name: transformers, enabling an automated code snippet to be displayed for easy usage with the transformers library, as evidenced by the config.json (Qwen2ForCausalLM architecture and transformers version).

These changes improve the model's visibility and usability for the community.

renhouxing changed pull request status to merged Sep 2, 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