README.md

---
base_model: deepseek-ai/deepseek-coder-6.7b-instruct
tags:
- SOLAR
- instruct
- finetune
model-index:
- name: NaturalQuery-Solar-6.7B-v0.1
  results: []
license: apache-2.0
language:
- en
datasets:
- wikisql
---

# **NaturalQuery-Solar-6.7B-v0.1**

**NaturalQuery** is a LLM that can translate natural language queries to SQL based on your schema.

NaturalQuery-v0.1 is finetuned on 8k text to PostgreSQL Natural Language <> SQL pairs.

**Future Improvements**:

- Much larger training set
- More complex schemas, questions, and queries
- Reward modeling via DPO
- Benchmarking

# **Usage**

Make sure you have the correct version of the transformers library installed:

```sh
pip install transformers==4.35.2
```

### **Loading the Model**

Use the following Python code to load the model:

```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("cfahlgren1/NaturalSQL-6.7B-v0")
model = AutoModelForCausalLM.from_pretrained(
    "cfahlgren1/NaturalSQL-6.7B-v0",
    device_map="auto",
    torch_dtype=torch.float16,
)
```

### **Generating Text**

To generate text, use the following Python code:

```python
text = "Hi, my name is "
inputs = tokenizer(text, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=64)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```


# **SQL Generation Template**

```
### Task 

Generate a SQL query to answer the following question: `{natural language question}` 

### Database Schema 

The query will run on a database with the following schema: 

'''
<SQL Table DDL Statements>
'''

### Answer 
Here is the SQL query that answers the question: `{natural language question}` 
'''sql
```

# **Example SQL Output**

### **Example Schemas**

```sql
 CREATE TABLE
      table_1_11545282_6 (
        "No." numeric,
        Nationality text,
        "Years for Jazz" text
      );
    
    CREATE TABLE
      table_2_17383560_1 (
        Pick numeric,
        Round numeric,
        Player text,
        "School/Club Team" text,
        Position text
      );
    
    CREATE TABLE
      table_1_10581768_2 (
        Institution text,
        Enrollment numeric,
        Nickname text,
        Founded numeric
      );
```

**Question**: **What is the round of pick 63?**
```sql
SELECT "Round" FROM table_2_17383560_1 WHERE Pick=63;
```
**Question**: **What is the most popular position among players?**
```sql
SELECT COUNT("Position") FROM "table_2_17383560_1" GROUP BY "Position" ORDER BY COUNT("Position") DESC LIMIT 1;
```

**Question**: **What is the most recent year an institution was founded?**
```sql
SELECT MAX("Founded") FROM table_1_10581768_2;
```