Instructions to use semiotic/T5-3B-SynQL-Spider-All-Run-01 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use semiotic/T5-3B-SynQL-Spider-All-Run-01 with Transformers:

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

pipe = pipeline("text-generation", model="semiotic/T5-3B-SynQL-Spider-All-Run-01")

# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("semiotic/T5-3B-SynQL-Spider-All-Run-01")
model = AutoModelForSeq2SeqLM.from_pretrained("semiotic/T5-3B-SynQL-Spider-All-Run-01", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use semiotic/T5-3B-SynQL-Spider-All-Run-01 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "semiotic/T5-3B-SynQL-Spider-All-Run-01"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "semiotic/T5-3B-SynQL-Spider-All-Run-01",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/semiotic/T5-3B-SynQL-Spider-All-Run-01

SGLang

How to use semiotic/T5-3B-SynQL-Spider-All-Run-01 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 "semiotic/T5-3B-SynQL-Spider-All-Run-01" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "semiotic/T5-3B-SynQL-Spider-All-Run-01",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "semiotic/T5-3B-SynQL-Spider-All-Run-01" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "semiotic/T5-3B-SynQL-Spider-All-Run-01",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use semiotic/T5-3B-SynQL-Spider-All-Run-01 with Docker Model Runner:
```
docker model run hf.co/semiotic/T5-3B-SynQL-Spider-All-Run-01
```

Model Card for T5-3B/SynQL-Spider-Train-Run-01

Developed by: Semiotic Labs
Model type: [Text to SQL]
License: [Apache-2.0]
Finetuned from model: google-t5/t5-3b
Dataset used for finetuning: semiotic/SynQL-Spider-Train

Model Context

Example metadata can be found below, context represents the prompt that is presented to the model. Database schemas follow the encoding method proposed by Shaw et al (2020).

"query": "SELECT count(*) FROM singer",
"question": "How many singers do we have?",
"context": "How many singers do we have? | concert_singer | stadium : stadium_id, location, name, capacity, highest, lowest, average | singer : singer_id, name, country, song_name, song_release_year, age, is_male | concert : concert_id, concert_name, theme, stadium_id, year | singer_in_concert : concert_id, singer_id",
"db_id": "concert_singer",

Model Results

Evaluation set: Spider/dev

Evaluation metrics: [Test-Suite-Execution, Execution Accuracy]

Model	Data	Run	Execution Accuracy	Test-Suite Execution Accuracy
T5-3B	semiotic/SynQL-Spider-Train	00	0.7021	0.5996
T5-3B	semiotic/SynQL-Spider-Train	01	0.6992	0.5464
T5-3B	semiotic/SynQL-Spider-Train	02	0.7002	0.5861

Downloads last month: 36

Model tree for semiotic/T5-3B-SynQL-Spider-All-Run-01

Base model

google-t5/t5-3b

Finetuned

(33)

this model

Dataset used to train semiotic/T5-3B-SynQL-Spider-All-Run-01

Paper for semiotic/T5-3B-SynQL-Spider-All-Run-01

Compositional Generalization and Natural Language Variation: Can a Semantic Parsing Approach Handle Both?

Paper • 2010.12725 • Published Oct 24, 2020