Instructions to use decompute/Nebula-S-SVMS2-3B-Internal with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use decompute/Nebula-S-SVMS2-3B-Internal with Transformers:

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

pipe = pipeline("text-generation", model="decompute/Nebula-S-SVMS2-3B-Internal")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("decompute/Nebula-S-SVMS2-3B-Internal")
model = AutoModelForCausalLM.from_pretrained("decompute/Nebula-S-SVMS2-3B-Internal")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use decompute/Nebula-S-SVMS2-3B-Internal with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "decompute/Nebula-S-SVMS2-3B-Internal"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "decompute/Nebula-S-SVMS2-3B-Internal",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/decompute/Nebula-S-SVMS2-3B-Internal

SGLang

How to use decompute/Nebula-S-SVMS2-3B-Internal 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 "decompute/Nebula-S-SVMS2-3B-Internal" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "decompute/Nebula-S-SVMS2-3B-Internal",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "decompute/Nebula-S-SVMS2-3B-Internal" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "decompute/Nebula-S-SVMS2-3B-Internal",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use decompute/Nebula-S-SVMS2-3B-Internal with Docker Model Runner:
```
docker model run hf.co/decompute/Nebula-S-SVMS2-3B-Internal
```

Nebula-S-SVMS2-3B-Internal

File size: 379 Bytes

a8bc0fd

{
  "python": "3.12.13 | packaged by conda-forge | (main, Mar  5 2026, 16:50:00) [GCC 14.3.0]",
  "python_version": "3.12.13",
  "packages": {
    "torch": "2.11.0",
    "transformers": "5.8.0",
    "safetensors": "0.7.0",
    "accelerate": "1.13.0",
    "huggingface_hub": "1.8.0"
  },
  "torch_cuda": "13.0",
  "torch_git_version": "70d99e998b4955e0049d13a98d77ae1b14db1f45"
}