Instructions to use Boakpe/Qwen3-4B-Thinking-2507-Text-to-SQL-Agent-FT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Boakpe/Qwen3-4B-Thinking-2507-Text-to-SQL-Agent-FT with Transformers:

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

pipe = pipeline("text-generation", model="Boakpe/Qwen3-4B-Thinking-2507-Text-to-SQL-Agent-FT")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("Boakpe/Qwen3-4B-Thinking-2507-Text-to-SQL-Agent-FT")
model = AutoModelForMultimodalLM.from_pretrained("Boakpe/Qwen3-4B-Thinking-2507-Text-to-SQL-Agent-FT")
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 Settings

vLLM

How to use Boakpe/Qwen3-4B-Thinking-2507-Text-to-SQL-Agent-FT with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Boakpe/Qwen3-4B-Thinking-2507-Text-to-SQL-Agent-FT"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Boakpe/Qwen3-4B-Thinking-2507-Text-to-SQL-Agent-FT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Boakpe/Qwen3-4B-Thinking-2507-Text-to-SQL-Agent-FT

SGLang

How to use Boakpe/Qwen3-4B-Thinking-2507-Text-to-SQL-Agent-FT 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 "Boakpe/Qwen3-4B-Thinking-2507-Text-to-SQL-Agent-FT" \
    --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": "Boakpe/Qwen3-4B-Thinking-2507-Text-to-SQL-Agent-FT",
		"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 "Boakpe/Qwen3-4B-Thinking-2507-Text-to-SQL-Agent-FT" \
        --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": "Boakpe/Qwen3-4B-Thinking-2507-Text-to-SQL-Agent-FT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Boakpe/Qwen3-4B-Thinking-2507-Text-to-SQL-Agent-FT with Docker Model Runner:
```
docker model run hf.co/Boakpe/Qwen3-4B-Thinking-2507-Text-to-SQL-Agent-FT
```

Qwen3-4B-Thinking-2507 Text-to-SQL Agent FT

This is a fine-tuned Qwen3-4B-Thinking-2507 model for agentic Text-to-SQL in Brazilian Portuguese. It was trained on filtered teacher trajectories so that a small local model can learn database-agent behavior: inspecting table metadata, executing exploratory SQL, recovering from SQL errors, and deciding whether to answer with SQL, ask for clarification, or abstain as unanswerable.

Code and reproducibility repository:

https://github.com/Boakpe/distilled-slms-for-text-to-sql-pt-br

Related collection:

https://huggingface.co/collections/Boakpe/distilled-slms-for-text-to-sql-pt-br

What This Model Is For

The model is intended to be used with the SQL-agent runtime in the GitHub repository. The runtime provides the tool interface used during training:

get_table_schema
execute_sql
final_answer

This is not a general chat model. It is specialized for tool-using Text-to-SQL workflows in Portuguese.

Training Data

The model was fine-tuned on:

https://huggingface.co/datasets/Boakpe/pt-br-agentic-text-to-sql-distilled-trajectories

The public dataset contains 7,442 message-only trajectories selected from LLM-judged correct agent conversations. Sensitive CPF/CNPJ-like values were pseudonymized before release.

Results

Primary benchmark: anonymized PostgreSQL/PostGIS environmental-registry database, 180 questions:

90 SQL
45 clarification
45 unanswerable

Model	Overall	Strict SQL	Relaxed SQL	Non-SQL	Clarification	Unanswerable	Runtime
Qwen3-4B-Thinking-2507 base	56.1	28.9	36.7	75.6	71.1	80.0	2h 42m
Qwen3-4B-Thinking FT	78.9	34.4	70.0	87.8	86.7	88.9	2h 01m
Qwen3.5-27B-Q3_K_M teacher	75.0	40.0	70.0	80.0	75.6	84.4	3h 52m

SQL accuracy by difficulty, relaxed execution:

Model	Easy	Medium	Hard	Expert
Qwen3-4B-Thinking-2507 base	70.0	43.3	20.0	0.0
Qwen3-4B-Thinking FT	80.0	86.7	63.3	20.0

Pass@K for the fine-tuned model:

Setting	Overall	Relaxed SQL	Non-SQL	Runtime
Pass@1	78.9	70.0	87.8	2h 01m
Pass@5	91.7	87.8	95.6	5h 31m

Out-of-domain benchmark: rede_saude_publica, 100 questions:

Model	Overall	SQL	Non-SQL
Qwen3-4B-Thinking-2507 base	70.0	64.0	76.0
Qwen3-4B-Thinking FT	75.0	72.0	78.0
Qwen3.5-27B-Q3_K_M teacher	82.0	90.0	74.0

Recommended Inference

For local inference, the GGUF Q8_0 export is usually easier:

https://huggingface.co/Boakpe/Qwen3-4B-Thinking-2507-Text-to-SQL-Agent-FT-GGUF

Use the GitHub repository for the runnable agent and benchmark setup:

https://github.com/Boakpe/distilled-slms-for-text-to-sql-pt-br

Limitations

The model is specialized for the released SQL-agent protocol.
It can generate plausible but semantically wrong SQL, especially on hard and expert questions.
It should not be used as a production decision system without independent SQL validation.
Results may depend on inference server support for tool calling and the chat template.

License

Apache 2.0.

Downloads last month: 14

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for Boakpe/Qwen3-4B-Thinking-2507-Text-to-SQL-Agent-FT

Base model

Qwen/Qwen3-4B-Thinking-2507

Finetuned

(244)

this model

Dataset used to train Boakpe/Qwen3-4B-Thinking-2507-Text-to-SQL-Agent-FT

Collection including Boakpe/Qwen3-4B-Thinking-2507-Text-to-SQL-Agent-FT

Distilled SLMs for Text-to-SQL (PT-BR)

Collection

Collection for the paper "On the Feasibility of Distilled Small Language Models for Agentic Text-to-SQL in Portuguese under Real-World Conditions". • 5 items • Updated 4 days ago