Instructions to use samadpls/querypls-prompt2sql with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use samadpls/querypls-prompt2sql with Transformers:

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

pipe = pipeline("text-generation", model="samadpls/querypls-prompt2sql")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("samadpls/querypls-prompt2sql")
model = AutoModelForCausalLM.from_pretrained("samadpls/querypls-prompt2sql")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use samadpls/querypls-prompt2sql with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "samadpls/querypls-prompt2sql"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "samadpls/querypls-prompt2sql",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/samadpls/querypls-prompt2sql

SGLang

How to use samadpls/querypls-prompt2sql 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 "samadpls/querypls-prompt2sql" \
    --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": "samadpls/querypls-prompt2sql",
		"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 "samadpls/querypls-prompt2sql" \
        --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": "samadpls/querypls-prompt2sql",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use samadpls/querypls-prompt2sql with Docker Model Runner:
```
docker model run hf.co/samadpls/querypls-prompt2sql
```

🛢💬 Querypls-Prompt2SQL

Overview

Querypls-Prompt2SQL is a 💬 text-to-SQL generation model developed by samadpls. It is designed for generating SQL queries based on user prompts.

Model Usage

To get started with the model in Python, you can use the following code:

from transformers import pipeline, AutoTokenizer

question = "how to get all employees from table0"
prompt = f'Your task is to create SQL query of the following {question}, just SQL query and no text'

tokenizer = AutoTokenizer.from_pretrained("samadpls/querypls-prompt2sql")
pipe = pipeline(task='text-generation', model="samadpls/querypls-prompt2sql", tokenizer=tokenizer, max_length=200)

result = pipe(prompt)
print(result[0]['generated_text'])

Adjust the question variable with the desired question, and the generated SQL query will be printed.

Training Details

The model was trained on Google Colab, and its purpose is to be used in the Querypls project with the following training and validation loss progression:

Step     Training Loss    Validation Loss
943      2.332100         2.652054
1886     2.895300         2.551685
2829     2.427800         2.498556
3772     2.019600         2.472013
4715     3.391200         2.465390

However, note that the model may be too large to load in certain environments.

For more information and details, please refer to the provided documentation.

Model Card Authors

🤖 samadpls

Downloads last month: 29

Safetensors

Model size

7B params

Tensor type

F32

F16

Collection including samadpls/querypls-prompt2sql

Querypls

Collection

Prompt-2-SQL • 2 items • Updated Nov 7, 2023