| Model Type | | autoregressive, text-to-SQL generation |
|
| Use Cases |
| Areas: | |
| Applications: | | Database querying, Natural language to SQL conversion |
|
| Primary Use Cases: | | Text-to-SQL generation, Database query formation |
|
| Considerations: | | The model should be used with the defined prompt format for optimal results. |
|
|
| Additional Notes | | Model is fine-tuned for SQL generation with predefined prompt format and designed to output SELECT queries. |
|
| Training Details |
| Data Sources: | | The Stack, 20 public sources for text-to-SQL pairs |
|
| Data Volume: | | 1M training samples from The Stack |
|
| Methodology: | | Cross-entropy loss for SQL generation tasks |
|
| Hardware Used: | |
| Model Architecture: | |
|