Update README.md

README.md

@@ -9,6 +9,9 @@ datasets:
 - wikisql
 ---
 
+widget:
+- text: "Is this review positive or negative? Review: Best cast iron skillet you will ever buy."
+
 ## Paper
 
 ## [NatSight: A framework for building domain agnostic Natural Language Interface to Databases for next-gen Augmented Analytics](https://dcal.iimb.ac.in/baiconf2022/full_papers/2346.pdf)
@@ -32,6 +35,31 @@ Experiment results on benchmark datasets show that our approach achieves a state
  For weights initialization, we used [facebook/bart-base](https://huggingface.co/facebook/bart-base) and fine-tune as sequence-to-sequence task.
 
 
+## Using Transformers🤗
+
+```python
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
+
+tokenizer = AutoTokenizer.from_pretrained("course5i/NatSight-bart-base-wikisql")
+model = AutoModelForSeq2SeqLM.from_pretrained("course5i/NatSight-bart-base-wikisql")
+
+# define input
+raw_nat_query = "What was the number of race that Kevin Curtain won?"
+query_mention_schema = "c0 | number <eom>  v4 | Kevin Curtain"
+table_header_schema = "c0 | No <eom> c1 | Date <eom> c2 | Round <eom> c3 | Circuit <eom> c4 | Pole_Position <eom> c5 | Fastest_Lap <eom> c6 | Race_winner <eom> c7 | Report"
+
+encoder_input = raw_nat_query + " </s> " + query_mention_schema + " </s> " + table_header_schema
+input_ids = tokenizer.encode(encoder_input, return_tensors="pt", add_special_tokens=True)
+
+generated_ids = model.generate(input_ids=input_ids, num_beams=5, max_length=128)
+preds = [tokenizer.decode(g, skip_special_tokens=True, clean_up_tokenization_spaces=True) for g in generated_ids]
+output = preds[0]
+
+print("Output generic SQL query: {}".format(output))
+
+# output
+"SELECT COUNT(c0) FROM TABLE WHERE c4 = v4"
+
 ## Intended uses & limitations
 
 More information needed