Update README.md

README.md

@@ -92,18 +92,18 @@ Addressing the power of LLM in fintuned downstream task. Implemented as a person
 
 # Load model directly
 ```python
-from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
+# Use a pipeline as a high-level helper
+from transformers import pipeline
 
-tokenizer = AutoTokenizer.from_pretrained("SwastikM/bart-large-nl2sql")
+sql_generator = pipeline("text2text-generation", model="SwastikM/bart-large-nl2sql")
 
-model = AutoModelForSeq2SeqLM.from_pretrained("SwastikM/bart-large-nl2sql")
 
 query_question_with_context = """sql_prompt: Which economic diversification efforts in
 the 'diversification' table have a higher budget than the average budget for all economic diversification efforts in the 'budget' table?
 sql_context: CREATE TABLE diversification (id INT, effort VARCHAR(50), budget FLOAT); CREATE TABLE
 budget (diversification_id INT, diversification_effort VARCHAR(50), amount FLOAT);"""
 
-sql = model.generate(text)
+sql = sql_generator(text)[0]['generated_text']
 
 print(sql)
 ```