Llama 2 7B Instruct Text2sql

🚀 Llama-2-7B-instruct-text2sql Model Card

This model is a fine - tuned version of Llama 2 with 7 billion parameters, specifically designed for text - to - SQL tasks. It can generate SQL queries from a database schema and a natural language question.

✨ Features

• Code completion.
• Infilling.
• Instructions / chat.

📦 Installation

To use the Llama - 2 - 7B - instruct - text2sql model, you need to install the necessary libraries first:

pip install -q accelerate==0.24.1 transformers==4.35.0 torch==2.1.0 torchvision==0.16.0 torchaudio==2.1.0

💻 Usage Examples

Basic Usage

The following code demonstrates how to use the Llama - 2 - 7B - instruct - text2sql model to generate SQL queries from natural language questions:

import torch
from transformers import (
    AutoModelForCausalLM,
    AutoTokenizer
)

model_name = 'support-pvelocity/Llama-2-7B-instruct-text2sql'

model = AutoModelForCausalLM.from_pretrained(model_name, device_map='auto', torch_dtype=torch.float16)
tokenizer = AutoTokenizer.from_pretrained(model_name)

table = "CREATE TABLE sales ( sale_id number PRIMARY KEY, product_id number, customer_id number, salesperson_id number, sale_date DATE, quantity number, FOREIGN KEY (product_id) REFERENCES products(product_id), FOREIGN KEY (customer_id) REFERENCES customers(customer_id), FOREIGN KEY (salesperson_id) REFERENCES salespeople(salesperson_id)); CREATE TABLE product_suppliers ( supplier_id number PRIMARY KEY, product_id number, supply_price number, FOREIGN KEY (product_id) REFERENCES products(product_id)); CREATE TABLE customers ( customer_id number PRIMARY KEY, name text, address text ); CREATE TABLE salespeople ( salesperson_id number PRIMARY KEY, name text, region text ); CREATE TABLE product_suppliers ( supplier_id number PRIMARY KEY, product_id number, supply_price number );"

question = 'Find the salesperson who made the most sales.'

prompt = f"[INST] Write SQLite query to answer the following question given the database schema. Please wrap your code answer using ```: Schema: {table} Question: {question} [/INST] Here is the SQLite query to answer to the question: {question}: ``` "

tokens = tokenizer(prompt, return_tensors="pt").to('cuda:0')
input_ids = tokens.input_ids

generated_ids = model.generate(input_ids=input_ids, max_length=4048, pad_token_id=tokenizer.eos_token_id)
output = tokenizer.decode(generated_ids[0], skip_special_tokens=True)
output = output.split('```')[2]
print(output)

📚 Documentation

Model Information

LoRA Parameters

bitsandbytes Parameters

Training Parameters

Intended Use

• Intended Use Cases: This model is for commercial and research use in English, designed for text - to - SQL tasks.
• Out - of - Scope Uses: Any use that violates applicable laws or regulations, use in languages other than English, or any other use prohibited by the Acceptable Use Policy and Licensing Agreement for Llama and its variants.

Model Architecture

Llama - 2 - 7B - instruct - text2sql is an auto - regressive language model using an optimized transformer architecture.

Model Dates

This model was trained between January 2023 and July 2023.

Ethical Considerations and Limitations

Llama - 2 - 7B - instruct - text2sql is a powerful language model, but it may produce inaccurate or objectionable responses in some cases. Safety testing and tuning are recommended before deploying it in specific applications.

Hardware and Software

Training Data

This model was trained and fine - tuned on the same data as Llama 2 with different weights.

Evaluation Results

For evaluation results, please refer to Section 3 and safety evaluations in Section 4 of the research paper.

📄 License

This model is governed by a custom commercial license from Llama. For details, please visit: Custom Commercial License