Instructions to use decula/sd with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use decula/sd with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.5-9B")
model = PeftModel.from_pretrained(base_model, "decula/sd")

Transformers

How to use decula/sd with Transformers:

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

pipe = pipeline("text-generation", model="decula/sd")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("decula/sd", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use decula/sd with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/decula/sd

SGLang

How to use decula/sd 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 "decula/sd" \
    --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": "decula/sd",
		"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 "decula/sd" \
        --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": "decula/sd",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use decula/sd with Docker Model Runner:
```
docker model run hf.co/decula/sd
```

sd / gemini_excel_rag.py

Commit History

Added 7b_dual.py

3bb71dd

decula commited on Feb 24

Added markitdown

e0fb7cc

decula commited on Jul 8, 2025

Remove Mark down

11f1cd7

decula commited on Jul 8, 2025

added langchain

ce31327

decula commited on Jul 8, 2025

Commit History

Added 7b_dual.py 3bb71dd

Added markitdown e0fb7cc

Remove Mark down 11f1cd7

added langchain ce31327

Added 7b_dual.py

3bb71dd

Added markitdown

e0fb7cc

Remove Mark down

11f1cd7

added langchain

ce31327