Instructions to use defog/sqlcoder-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use defog/sqlcoder-7b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="defog/sqlcoder-7b")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("defog/sqlcoder-7b") model = AutoModelForCausalLM.from_pretrained("defog/sqlcoder-7b") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use defog/sqlcoder-7b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "defog/sqlcoder-7b" # 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-7b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/defog/sqlcoder-7b
- SGLang
How to use defog/sqlcoder-7b 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-7b" \ --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-7b", "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-7b" \ --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-7b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use defog/sqlcoder-7b with Docker Model Runner:
docker model run hf.co/defog/sqlcoder-7b
Commit ·
cb59ea2
1
Parent(s): 8638168
Update README.md
Browse files
README.md
CHANGED
|
@@ -14,7 +14,7 @@ Defog's SQLCoder is a state-of-the-art LLM for converting natural language quest
|
|
| 14 |
## TL;DR
|
| 15 |
SQLCoder-7B is a 7B parameter model that outperforms `gpt-3.5-turbo` for natural language to SQL generation tasks on our [sql-eval](https://github.com/defog-ai/sql-eval) framework, and significantly outperforms all popular open-source models. When fine-tuned on a given schema, it also outperforms `gpt-4`
|
| 16 |
|
| 17 |
-
SQLCoder is fine-tuned on a base
|
| 18 |
|
| 19 |
## Results on novel datasets not seen in training
|
| 20 |
| model | perc_correct |
|
|
|
|
| 14 |
## TL;DR
|
| 15 |
SQLCoder-7B is a 7B parameter model that outperforms `gpt-3.5-turbo` for natural language to SQL generation tasks on our [sql-eval](https://github.com/defog-ai/sql-eval) framework, and significantly outperforms all popular open-source models. When fine-tuned on a given schema, it also outperforms `gpt-4`
|
| 16 |
|
| 17 |
+
SQLCoder-7B is fine-tuned on a base Mistral-7B model.
|
| 18 |
|
| 19 |
## Results on novel datasets not seen in training
|
| 20 |
| model | perc_correct |
|