Instructions to use gaussalgo/T5-LM-Large-text2sql-spider with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use gaussalgo/T5-LM-Large-text2sql-spider with Transformers:

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

pipe = pipeline("text-generation", model="gaussalgo/T5-LM-Large-text2sql-spider")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("gaussalgo/T5-LM-Large-text2sql-spider")
model = AutoModelForSeq2SeqLM.from_pretrained("gaussalgo/T5-LM-Large-text2sql-spider")
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

vLLM

How to use gaussalgo/T5-LM-Large-text2sql-spider with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "gaussalgo/T5-LM-Large-text2sql-spider"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "gaussalgo/T5-LM-Large-text2sql-spider",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/gaussalgo/T5-LM-Large-text2sql-spider

SGLang

How to use gaussalgo/T5-LM-Large-text2sql-spider 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 "gaussalgo/T5-LM-Large-text2sql-spider" \
    --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": "gaussalgo/T5-LM-Large-text2sql-spider",
		"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 "gaussalgo/T5-LM-Large-text2sql-spider" \
        --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": "gaussalgo/T5-LM-Large-text2sql-spider",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use gaussalgo/T5-LM-Large-text2sql-spider with Docker Model Runner:
```
docker model run hf.co/gaussalgo/T5-LM-Large-text2sql-spider
```

Sample code correction

by Rasha-Ragab - opened Dec 9, 2023

Discussion

Rasha-Ragab

Dec 9, 2023

•

edited Dec 9, 2023

The sample code given to run a sample example needs the following change: use tokenizer.batch_decode(sequences=outputs, skip_special_tokens=True) instead of tokenizer.decode so the code can run correctly.

#Code given:
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer

#model_path = 'gaussalgo/T5-LM-Large-text2sql-spider'
model = AutoModelForSeq2SeqLM.from_pretrained(modelPath)
tokenizer = AutoTokenizer.from_pretrained(modelPath)

question = "What is the average, minimum, and maximum age for all French musicians?"
schema = """
"stadium" "Stadium_ID" int , "Location" text , "Name" text , "Capacity" int , "Highest" int , "Lowest" int , "Average" int , foreign_key: primary key: "Stadium_ID" [SEP] "singer" "Singer_ID" int , "Name" text , "Country" text , "Song_Name" text , "Song_release_year" text , "Age" int , "Is_male" bool , foreign_key: primary key: "Singer_ID" [SEP] "concert" "concert_ID" int , "concert_Name" text , "Theme" text , "Year" text , foreign_key: "Stadium_ID" text from "stadium" "Stadium_ID" , primary key: "concert_ID" [SEP] "singer_in_concert" foreign_key: "concert_ID" int from "concert" "concert_ID" , "Singer_ID" text from "singer" "Singer_ID" , primary key: "concert_ID" "Singer_ID"
"""

input_text = " ".join(["Question: ",question, "Schema:", schema])

model_inputs = tokenizer(input_text, return_tensors="pt")
outputs = model.generate(**model_inputs, max_length=512)

output_text = tokenizer.batch_decode(sequences=outputs, skip_special_tokens=True) ## changed the decode to batch decode so the code run successfully

print("SQL Query:")
print(output_text)

michal-stefanik

Gauss Algorithmic org Jun 12, 2025

Hi @Rasha-Ragab , thanks for pointing this out! I hope we managed to incorporate your suggestion.

michal-stefanik changed discussion status to closed Jun 12, 2025

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment