README.md

---
library_name: transformers
license: apache-2.0
---

# Mistral-7B-Instruct-SQL-ian

## About the Model

<!-- Provide a longer summary of what this model is. -->

This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.3. https://huggingface.co/datasets/gretelai/synthetic_text_to_sql

- **Model Name:** Mistral-7B-Instruct-SQL-ian
- **Developed by:** kubwa
- **Base Model Name:** mistralai/Mistral-7B-Instruct-v0.3
- **Base Model URL:** [Mistral-7B-Instruct-v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3)
- **Dataset Name:** gretelai/synthetic_text_to_sql
- **Dataset URL:** [synthetic_text_to_sql](https://huggingface.co/datasets/gretelai/synthetic_text_to_sql)
- **Dataset Description:** gretelai/synthetic_text_to_sql is a rich dataset of high quality synthetic Text-to-SQL samples, designed and generated using Gretel Navigator, and released under Apache 2.0.
- **License:** Apache-2.0
- 
## Prompt Template

```
<s>
### Instruction:
{question}

### Context:
{schema}

### Response:</s>
```

## How to Use it

```python
from transformers import AutoTokenizer
from transformers import AutoModelForCausalLM
import torch

model = AutoModelForCausalLM.from_pretrained("kubwa/Mistral-7B-Instruct-SQL-ian", low_cpu_mem_usage=True)
tokenizer = AutoTokenizer.from_pretrained("kubwa/Mistral-7B-Instruct-SQL-ian", use_fast=True)

text = """<s>
### Instruction:
What is the total volume of timber sold by each salesperson, sorted by salesperson?

### Context:
CREATE TABLE salesperson (salesperson_id INT, name TEXT, region TEXT); INSERT INTO salesperson (salesperson_id, name, region) VALUES (1, 'John Doe', 'North'), (2, 'Jane Smith', 'South'); CREATE TABLE timber_sales (sales_id INT, salesperson_id INT, volume REAL, sale_date DATE); INSERT INTO timber_sales (sales_id, salesperson_id, volume, sale_date) VALUES (1, 1, 120, '2021-01-01'), (2, 1, 150, '2021-02-01'), (3, 2, 180, '2021-01-01');

### Response:</s>
"""
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
inputs = tokenizer(text, return_tensors="pt").to(device)

outputs = model.generate(**inputs, max_new_tokens=300, pad_token_id=tokenizer.eos_token_id)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```

## Example Output

  ```
    ### Instruction:
    What is the total volume of timber sold by each salesperson, sorted by salesperson?
    
    ### Context:
    CREATE TABLE salesperson (salesperson_id INT, name TEXT, region TEXT); INSERT INTO salesperson (salesperson_id, name, region) VALUES (1, 'John Doe', 'North'), (2, 'Jane Smith', 'South'); CREATE TABLE timber_sales (sales_id INT, salesperson_id INT, volume REAL, sale_date DATE); INSERT INTO timber_sales (sales_id, salesperson_id, volume, sale_date) VALUES (1, 1, 120, '2021-01-01'), (2, 1, 150, '2021-02-01'), (3, 2, 180, '2021-01-01');
    
    ### Response: 
    To get the total volume of timber sold by each salesperson, we can use a SQL query that groups the data by salesperson_id and sums the volume column. Here's the query:
    
    ```sql
    SELECT salesperson_id, name, SUM(volume) as total_volume
    FROM timber_sales
    JOIN salesperson ON timber_sales.salesperson_id = salesperson.salesperson_id
    GROUP BY salesperson_id, name
    ORDER BY total_volume DESC;
    ```
    
    This query will return the following result:
    
    ```
    salesperson_id | name       | total_volume
    --------------+------------+---------------
    1            | John Doe    | 270
    2            | Jane Smith  | 180
    ```
    
    This result shows that John Doe sold a total of 270 cubic units of timber, while Jane Smith sold 180 cubic units. The result is sorted by the total volume in descending order.
  ```