Instructions to use twinkle-ai/twinkle-sqlcoder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use twinkle-ai/twinkle-sqlcoder with Transformers:

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

pipe = pipeline("text-generation", model="twinkle-ai/twinkle-sqlcoder")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("twinkle-ai/twinkle-sqlcoder")
model = AutoModelForCausalLM.from_pretrained("twinkle-ai/twinkle-sqlcoder")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use twinkle-ai/twinkle-sqlcoder with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/twinkle-ai/twinkle-sqlcoder

SGLang

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

Docker Model Runner
How to use twinkle-ai/twinkle-sqlcoder with Docker Model Runner:
```
docker model run hf.co/twinkle-ai/twinkle-sqlcoder
```

Devstral SQLCoder SFT

This model is a full-parameter SFT checkpoint for SQL generation, trained from mistralai/Devstral-Small-2505 and exported to Hugging Face safetensors format.

Model Details

Base model: mistralai/Devstral-Small-2505
Architecture: MistralForCausalLM
Precision used in training: bf16
Max sequence length (training config): 4096
Export format: sharded safetensors with model.safetensors.index.json

Training Data (Merged)

The SFT run merged the following datasets:

spider
bird
bird23-train-filtered
synsql-2.5m
wikisql
gretelai-synthetic
sql-create-context

Intended Use

Text-to-SQL research and experimentation
SQL generation benchmarks and evaluation pipelines

Limitations

This model may generate incorrect SQL and should be validated before production use.
Performance depends on prompt format, schema context quality, and decoding settings.
Evaluate safety and compliance requirements before deployment.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

repo_or_path = "<hf-username-or-org>/<model-repo>"

tokenizer = AutoTokenizer.from_pretrained(repo_or_path, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    repo_or_path,
    torch_dtype="bfloat16",
)