Instructions to use thenewth/EXAONE-4-32B-text2sql with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use thenewth/EXAONE-4-32B-text2sql with Transformers:

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

pipe = pipeline("text-generation", model="thenewth/EXAONE-4-32B-text2sql")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("thenewth/EXAONE-4-32B-text2sql")
model = AutoModelForCausalLM.from_pretrained("thenewth/EXAONE-4-32B-text2sql", device_map="auto")
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 thenewth/EXAONE-4-32B-text2sql with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "thenewth/EXAONE-4-32B-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": "thenewth/EXAONE-4-32B-text2sql",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/thenewth/EXAONE-4-32B-text2sql

SGLang

How to use thenewth/EXAONE-4-32B-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 "thenewth/EXAONE-4-32B-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": "thenewth/EXAONE-4-32B-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 "thenewth/EXAONE-4-32B-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": "thenewth/EXAONE-4-32B-text2sql",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use thenewth/EXAONE-4-32B-text2sql with Docker Model Runner:
```
docker model run hf.co/thenewth/EXAONE-4-32B-text2sql
```

Model Details

Model Description

한국어로 작성된 자연어 질문을 SQL 쿼리로 변환하는 텍스트2SQL 모델입니다.
LGAI-EXAONE 기반으로 한국어 데이터에 특화된 파인튜닝 진행.

Developed by: Donghyun Kim
Language(s) (NLP): 한국어, 영어
License: Apache 2.0

Uses

한국어 기반의 SQL 생성이 필요한 데이터 분석 툴이나 챗봇 등에 사용 가능.

Bias, Risks, and Limitations

비정형 질문이나 데이터베이스 구조가 명확하지 않은 경우 정확도가 떨어질 수 있음.

Downloads last month: 8

Safetensors

Model size

32B params

Tensor type

F16

Model tree for thenewth/EXAONE-4-32B-text2sql

Base model

LGAI-EXAONE/EXAONE-4.0-32B

Finetuned

(8)

this model

thenewth
/

EXAONE-4-32B-text2sql

Model Details

Model Description

Uses

Bias, Risks, and Limitations

Model tree for thenewth/EXAONE-4-32B-text2sql

Dataset used to train thenewth/EXAONE-4-32B-text2sql