Instructions to use OneGate/OGSQL-Mistral-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OneGate/OGSQL-Mistral-7B with Transformers:

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

pipe = pipeline("text-generation", model="OneGate/OGSQL-Mistral-7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("OneGate/OGSQL-Mistral-7B")
model = AutoModelForCausalLM.from_pretrained("OneGate/OGSQL-Mistral-7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use OneGate/OGSQL-Mistral-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OneGate/OGSQL-Mistral-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OneGate/OGSQL-Mistral-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/OneGate/OGSQL-Mistral-7B

SGLang

How to use OneGate/OGSQL-Mistral-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 "OneGate/OGSQL-Mistral-7B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OneGate/OGSQL-Mistral-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "OneGate/OGSQL-Mistral-7B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OneGate/OGSQL-Mistral-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use OneGate/OGSQL-Mistral-7B with Docker Model Runner:
```
docker model run hf.co/OneGate/OGSQL-Mistral-7B
```

OGSQL-Mistral-7B / README.md

MatrixIA

Update README.md

6771490 verified about 2 years ago

preview code

raw

history blame contribute delete

2.14 kB

	---
	license: cc-by-4.0
	tags:
	- Text-to-sql
	library_name: transformers
	---
	# OGSQL-Mistral7B

	![image/png](https://cdn-uploads.huggingface.co/production/uploads/65fc0d4cae01a24b4004a011/Efvejrv0b9Vruks9ez6UU.png)

	### Model Description
	OGSQL-Mistral7B was fine-tuned for the task of converting natural language text into SQL queries.


	- Model type: Mixture Of Experts (MoE)
	- Language(s) (NLP): SQL (target language for generation)
	- Finetuned from model: Mistral 7B instruct

	## Use Case
	OGSQL-7B is designed to facilitate the conversion of natural language queries into structured SQL commands, aiding in database querying without the need for manual SQL knowledge.

	## How to Get Started with the Model
	```python
	# Example code to load and use the model
	from transformers import AutoModelForSeq2SeqLM, AutoTokenizer

	model_name = "OGSQL-Mistral7B"
	tokenizer = AutoTokenizer.from_pretrained(model_name)
	model = AutoModelForSeq2SeqLM.from_pretrained(model_name)

	def generate_sql(query):
	inputs = tokenizer.encode(query, return_tensors="pt")
	outputs = model.generate(inputs)
	return tokenizer.decode(outputs[0], skip_special_tokens=True)

	# Example use
	query = """
	using this context:
	-- Create Customers Table
	CREATE TABLE Customers (
	customer_id INTEGER PRIMARY KEY,
	name TEXT NOT NULL,
	email TEXT,
	join_date DATE
	);

	-- Create Products Table
	CREATE TABLE Products (
	product_id INTEGER PRIMARY KEY,
	name TEXT NOT NULL,
	price DECIMAL(10, 2)
	);

	-- Create Orders Table
	CREATE TABLE Orders (
	order_id INTEGER PRIMARY KEY,
	customer_id INTEGER,
	product_id INTEGER,
	order_date DATE,
	quantity INTEGER,
	total_price DECIMAL(10, 2),
	FOREIGN KEY (customer_id) REFERENCES Customers(customer_id),
	FOREIGN KEY (product_id) REFERENCES Products(product_id)
	);

	show me all the orders from last month , sort by date


	"""
	print(generate_sql(query))

	```


	## alternatively you can use this notebook:
	[![Colab notebook](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1pQuIuCdoFMG76AH3BNZzep8PgRaZkkYS?usp=sharing)