Instructions to use Ellbendls/Qwen-3-4b-Text_to_SQL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Ellbendls/Qwen-3-4b-Text_to_SQL with Transformers:

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

pipe = pipeline("text-generation", model="Ellbendls/Qwen-3-4b-Text_to_SQL")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Ellbendls/Qwen-3-4b-Text_to_SQL")
model = AutoModelForCausalLM.from_pretrained("Ellbendls/Qwen-3-4b-Text_to_SQL")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Ellbendls/Qwen-3-4b-Text_to_SQL with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Ellbendls/Qwen-3-4b-Text_to_SQL"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ellbendls/Qwen-3-4b-Text_to_SQL",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Ellbendls/Qwen-3-4b-Text_to_SQL

SGLang

How to use Ellbendls/Qwen-3-4b-Text_to_SQL 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 "Ellbendls/Qwen-3-4b-Text_to_SQL" \
    --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": "Ellbendls/Qwen-3-4b-Text_to_SQL",
		"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 "Ellbendls/Qwen-3-4b-Text_to_SQL" \
        --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": "Ellbendls/Qwen-3-4b-Text_to_SQL",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Ellbendls/Qwen-3-4b-Text_to_SQL with Docker Model Runner:
```
docker model run hf.co/Ellbendls/Qwen-3-4b-Text_to_SQL
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Fine-Tuned LLM for Text-to-SQL Conversion

This model is a fine-tuned version of Qwen/Qwen3-4B designed to convert natural language queries into SQL statements. It was trained on the gretelai/synthetic_text_to_sql dataset and can provide both SQL queries and table schema context when needed.

Model Details

Model Description

This model has been fine-tuned to help users generate SQL queries based on natural language prompts. In scenarios where table schema context is missing, the model is trained to generate schema definitions along with the SQL query. The base Qwen-3-4B provides stronger multilingual support and larger context windows.

Base Model: Qwen/Qwen3-4B-Instruct-2507
Dataset: Gretel AI Synthetic Text-to-SQL Dataset
Languages Supported (base): many including English, Chinese, etc.
License: Apache-2.0

Key Features

Text-to-SQL Conversion: Converts natural language queries into accurate SQL statements.
Schema Generation: Generates table schema context when none is provided.
Optimized for Analytics and Reporting: Handles SQL queries with aggregation, grouping, filtering.
Multilingual Capabilities: Base model is trained on 119 languages/dialects. :contentReference[oaicite:0]{index=0}
Large Context Window: Qwen-3-4B uses long context length (32K tokens in many cases). :contentReference[oaicite:1]{index=1}

Usage

Direct Use

from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Ellbendls/Qwen-3-4B-Text_to_SQL")
model = AutoModelForCausalLM.from_pretrained("Ellbendls/Qwen-3-4B-Text_to_SQL")

# Input prompt
query = "What is the average salary by department in 2024?"

# Tokenize input and generate output
inputs = tokenizer(query, return_tensors="pt")
outputs = model.generate(**inputs, max_length=512)

# Decode and print
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Downloads last month: 44

Safetensors

Model size

4B params

Tensor type

F16

Model tree for Ellbendls/Qwen-3-4b-Text_to_SQL

Base model

Qwen/Qwen3-4B-Instruct-2507

Finetuned

(1706)

this model

Finetunes

1 model

Quantizations