Update README.md
Browse files
README.md
CHANGED
@@ -31,9 +31,9 @@ AI2SQL is designed for data analysts, business intelligence professionals, and d
|
|
31 |
AI2SQL is designed for efficient real-time inference, making it suitable for interactive applications where users query databases using natural language.
|
32 |
|
33 |
### Computational Requirements
|
34 |
-
- **Hardware Requirements**: AI2SQL performs optimally on
|
35 |
-
- **Memory Footprint**: The model requires
|
36 |
-
- **Latency**: The average response time for generating a SQL query is
|
37 |
|
38 |
### Usage Guidelines
|
39 |
To use AI2SQL for generating SQL queries, follow these steps:
|
|
|
31 |
AI2SQL is designed for efficient real-time inference, making it suitable for interactive applications where users query databases using natural language.
|
32 |
|
33 |
### Computational Requirements
|
34 |
+
- **Hardware Requirements**: AI2SQL performs optimally on a range of CPUs, showing satisfactory performance on an A10 processor. For enhanced performance, particularly for more complex queries, the use of a high-end CPU or GPU is recommended.
|
35 |
+
- **Memory Footprint**: The model requires at least 14 GB of RAM for inference.
|
36 |
+
- **Latency**: The average response time for generating a SQL query is dependent on the hardware used and the complexity of the query. On an A10 processor, latency is satisfactory, with potential for faster response times on more advanced hardware.
|
37 |
|
38 |
### Usage Guidelines
|
39 |
To use AI2SQL for generating SQL queries, follow these steps:
|