Update README.md

README.md

@@ -14,6 +14,90 @@ datasets:
 - gretelai/synthetic_text_to_sql
 ---
 
+# Text2SQL-1.5B Model
+
+## Overview
+**Text2SQL-1.5B** is a powerful **natural language to SQL** model designed to convert user queries into structured SQL statements. It supports complex multi-table queries and ensures high accuracy in text-to-SQL conversion.
+
+## System Instruction
+To ensure consistency in model outputs, use the following system instruction:
+
+> **Always separate code and explanation. Return SQL code in a separate block, followed by the explanation in a separate paragraph. Use markdown triple backticks (` ```sql ` for SQL) to format the code properly. Write the SQL query first in a separate code block. Then, explain the query in plain text. Do not merge them into one response.
+
+## Prompt Format
+The prompt format should include both the user query and the table structure using a `CREATE TABLE` statement. The expected message format should be:
+
+```json
+messages = [
+    {"role": "system", "content": "Always separate code and explanation. Return SQL code in a separate block, followed by the explanation in a separate paragraph. Use markdown triple backticks (```sql for SQL) to format the code properly. Write the SQL query first in a separate code block. Then, explain the query in plain text. Do not merge them into one response. The query should always include the table structure using a CREATE TABLE statement before executing the main SQL query."},
+    {"role": "user", "content": "Show the total sales for each customer who has spent more than $50,000."},
+    {"role": "user", "content": "
+CREATE TABLE sales (
+    id INT PRIMARY KEY,
+    customer_id INT,
+    total_amount DECIMAL(10,2),
+    FOREIGN KEY (customer_id) REFERENCES customers(id)
+);
+
+CREATE TABLE customers (
+    id INT PRIMARY KEY,
+    name VARCHAR(255)
+);
+"}
+] 
+```
+
+## Model Usage
+
+### **Using the Model for Text-to-SQL Conversion**
+The following code demonstrates how to use the model to convert natural language queries into SQL statements:
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
+
+# Load tokenizer and model
+tokenizer = AutoTokenizer.from_pretrained("yasserrmd/Text2SQL-1.5B")
+model = AutoModelForCausalLM.from_pretrained("yasserrmd/Text2SQL-1.5B")
+
+# Define the pipeline
+pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)
+
+# Define system instruction
+system_instruction = "Always separate code and explanation. Return SQL code in a separate block, followed by the explanation in a separate paragraph. Use markdown triple backticks (```sql for SQL) to format the code properly. Write the SQL query first in a separate code block. Then, explain the query in plain text. Do not merge them into one response. The query should always include the table structure using a CREATE TABLE statement before executing the main SQL query."
+
+# Define user query
+user_query = "Show the total sales for each customer who has spent more than $50,000.
+CREATE TABLE sales (
+    id INT PRIMARY KEY,
+    customer_id INT,
+    total_amount DECIMAL(10,2),
+    FOREIGN KEY (customer_id) REFERENCES customers(id)
+);
+
+CREATE TABLE customers (
+    id INT PRIMARY KEY,
+    name VARCHAR(255)
+);
+"
+
+# Define messages for input
+messages = [
+    {"role": "system", "content": system_instruction},
+    {"role": "user", "content": user_query},
+]
+
+# Generate SQL output
+response = pipe(messages)
+
+
+# Print the generated SQL query
+print(response[0]['generated_text'])
+```
+
+
+
+
+
 # Uploaded  model
 
 - **Developed by:** yasserrmd