Instructions to use Tuana/qwen35-08b-text2sql with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Tuana/qwen35-08b-text2sql with Transformers:

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

pipe = pipeline("text-generation", model="Tuana/qwen35-08b-text2sql")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("Tuana/qwen35-08b-text2sql")
model = AutoModelForImageTextToText.from_pretrained("Tuana/qwen35-08b-text2sql")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Tuana/qwen35-08b-text2sql with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Tuana/qwen35-08b-text2sql"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Tuana/qwen35-08b-text2sql",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Tuana/qwen35-08b-text2sql

SGLang

How to use Tuana/qwen35-08b-text2sql 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 "Tuana/qwen35-08b-text2sql" \
    --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": "Tuana/qwen35-08b-text2sql",
		"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 "Tuana/qwen35-08b-text2sql" \
        --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": "Tuana/qwen35-08b-text2sql",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Tuana/qwen35-08b-text2sql with Docker Model Runner:
```
docker model run hf.co/Tuana/qwen35-08b-text2sql
```

qwen35-08b-text2sql / README.md

Tuana

Create README.md

ed6c634 verified 14 days ago

preview code

raw

history blame contribute delete

1.85 kB

	---
	license: apache-2.0
	base_model: Qwen/Qwen3.5-0.8B
	library_name: transformers
	pipeline_tag: text-generation
	tags:
	- text-to-sql
	- sql
	- qwen
	- demo
	- vertex-ai
	- synthetic-data
	---

	# qwen35-08b-text2sql

	`Tuana/qwen35-08b-text2sql` is a demo Text-to-SQL model fine-tuned from [`Qwen/Qwen3.5-0.8B`](https://huggingface.co/Qwen/Qwen3.5-0.8B).

	It was fine-tuned on a small, specific synthetic SQL dataset for demonstration purposes. It is not intended to be a general Text-to-SQL model for arbitrary schemas or production databases.

	## Model Details

	- Base model: `Qwen/Qwen3.5-0.8B`
	- Task demo: Text-to-SQL style SQL generation
	- Fine-tuning method: LoRA SFT, merged into a full checkpoint
	- Training platform: Google Cloud Vertex AI
	- Training container: Hugging Face PyTorch Training Deep Learning Container
	- Dataset: `Tuana/synthetic-sql-dataset`
	- Model format: Merged `transformers` checkpoint

	## What This Model Demonstrates

	This model demonstrates a small fine-tuning workflow:

	1. Generate a synthetic SQL instruction dataset
	2. Fine-tune a small Qwen base model on Vertex AI
	3. Merge the LoRA adapter into the base checkpoint
	4. Serve or compare the result in a small demo app

	The demo dataset uses a small synthetic database domain with tables such as:

	- `department`
	- `management`
	- `head`

	The model should be viewed as a demo artifact for this specific setup, not as a robust SQL assistant.

	## Example Prompt Format

	```text
	Given this database schema:
	CREATE TABLE department (
	department_id VARCHAR,
	name VARCHAR,
	creation VARCHAR
	);
	CREATE TABLE management (
	department_id VARCHAR,
	head_id VARCHAR,
	temporary_acting VARCHAR
	);
	CREATE TABLE head (
	head_id VARCHAR,
	name VARCHAR,
	born_state VARCHAR
	);

	Write a SQL query for:
	List all department names.

	SQL:
	```