Instructions to use defog/sqlcoder-70b-alpha with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use defog/sqlcoder-70b-alpha with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="defog/sqlcoder-70b-alpha")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("defog/sqlcoder-70b-alpha") model = AutoModelForCausalLM.from_pretrained("defog/sqlcoder-70b-alpha") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use defog/sqlcoder-70b-alpha with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "defog/sqlcoder-70b-alpha" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "defog/sqlcoder-70b-alpha", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/defog/sqlcoder-70b-alpha
- SGLang
How to use defog/sqlcoder-70b-alpha 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 "defog/sqlcoder-70b-alpha" \ --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": "defog/sqlcoder-70b-alpha", "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 "defog/sqlcoder-70b-alpha" \ --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": "defog/sqlcoder-70b-alpha", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use defog/sqlcoder-70b-alpha with Docker Model Runner:
docker model run hf.co/defog/sqlcoder-70b-alpha
SQLite compatibility
Is there any way, or any prompt template that can be used to produce SQLite or any other database syntax?
Hi @khuswanto , SQLite has the most "liberal" syntax based on our limited understanding so whatever we generate (for postgres by default) should work for SQLite in most cases. We have tested lightly with snowflake and bigquery, and the generated syntax does align for all of the question types in our evaluation framework (https://github.com/defog-ai/sql-eval). For other databases, you can add explicit instructions to steer the model to use their specific syntax. For example, use TOP instead of LIMIT for SQL Server etc.