Instructions to use LarkAI/bart_large_nl2sql with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use LarkAI/bart_large_nl2sql with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="LarkAI/bart_large_nl2sql")# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("LarkAI/bart_large_nl2sql") model = AutoModel.from_pretrained("LarkAI/bart_large_nl2sql") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use LarkAI/bart_large_nl2sql with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "LarkAI/bart_large_nl2sql" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "LarkAI/bart_large_nl2sql", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/LarkAI/bart_large_nl2sql
- SGLang
How to use LarkAI/bart_large_nl2sql 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 "LarkAI/bart_large_nl2sql" \ --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": "LarkAI/bart_large_nl2sql", "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 "LarkAI/bart_large_nl2sql" \ --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": "LarkAI/bart_large_nl2sql", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use LarkAI/bart_large_nl2sql with Docker Model Runner:
docker model run hf.co/LarkAI/bart_large_nl2sql
Primary and Foreign keys
#1
by talhaty - opened
Can i use this, if i have multiple tables in the database and i have to collect data from these tables by using primary and foreign keys.
This model use wikisql data to train, this dataset is single table and single turn. If you want multi-table, may be you need use spider data for training and restructure the data.
You can reference https://huggingface.co/datasets/laion/OIG#unified_sqlv1jsonl-17000 and https://huggingface.co/datasets/laion/OIG#unified_sqlv2jsonl24000.
New version for multi-table: LarkAI/codet5p-770m_nl2sql_oig