Update README.md

README.md

@@ -25,8 +25,8 @@ This model is based on the declare-lab/flan-alpaca-base model finetuned with wik
 
 ## Uses
 
-The model generates a string of SQL query based on a question and MySQL table schema. 
-You can modify the table schema to match MySQL table schema if you are using different type of SQL database (e.g. PostgreSQL, Oracle, etc).
+The model generates a string of SQL query based on a question and table columns. **The generated query always uses "table" as the table name**. 
+Feel free to change the table name in the generated query to match your actual SQL table. 
 The generated SQL query can be run perfectly on the python SQL connection (e.g. psycopg2, mysql_connector, etc).
 
 #### Limitations
@@ -42,7 +42,7 @@ The generated SQL query can be run perfectly on the python SQL connection (e.g.
 ```
 ### Output Example
 ```python
-"""SELECT * FROM table_1341598_10 WHERE district = "Florida 18""""
+"""SELECT * FROM table WHERE district = "Florida 18""""
 ```
 
 ### How to use
@@ -59,7 +59,6 @@ model_ = AutoModelForSeq2SeqLM.from_pretrained(config.base_model_name_or_path, r
 tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path)
 
 model = PeftModel.from_pretrained(model_, model_id)
-model = get_peft_model(model,config)
 ```
 
 Model inference