Instructions to use defog/sqlcoder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use defog/sqlcoder with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="defog/sqlcoder")# Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("defog/sqlcoder") model = AutoModelForMultimodalLM.from_pretrained("defog/sqlcoder") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use defog/sqlcoder with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "defog/sqlcoder" # 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", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/defog/sqlcoder
- SGLang
How to use defog/sqlcoder 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" \ --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", "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" \ --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", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use defog/sqlcoder with Docker Model Runner:
docker model run hf.co/defog/sqlcoder
Fine tuning the Defog/sqlcoder
Hi, I know this question has been asked before. I do know that there are tonnes of tutorials available that gives hint at what needs to be done for fine tuning. What I am little bit concerned about is the prompt. Can I just use the prompt that defog shared with "answer" portion filled out with sql queries on custom data during fine tuning? Thanks
Hi @scigeek you can use our default prompt or you can use a different/varied prompt structure - we don't make guarantees but from our anecdotal experience switching up the prompt format doesn't change the performance significantly
Ok. Great! Thanks.