Create README.md

README.md

@@ -0,0 +1,34 @@
+TAPEX model fine-tuned on WTQ.
+
+To load it and run inference, you can do the following:
+
+from transformers import BartTokenizer, BartForConditionalGeneration
+import pandas as pd
+
+tokenizer = BartTokenizer.from_pretrained("nielsr/tapex-large-finetuned-wtq")
+model = BartForConditionalGeneration.from_pretrained("nielsr/tapex-large-finetuned-wtq")
+
+# create table
+data = {'Actors': ["Brad Pitt", "Leonardo Di Caprio", "George Clooney"], 'Number of movies': ["87", "53", "69"]}
+table = pd.DataFrame.from_dict(data)
+
+# turn into dict
+table_dict = {"header": list(table.columns), "rows": [list(row.values) for i,row in table.iterrows()]}
+
+# turn into format TAPEX expects
+# define the linearizer based on this code: https://github.com/microsoft/Table-Pretraining/blob/main/tapex/processor/table_linearize.py
+linearizer = IndexedRowTableLinearize()
+linear_table = linearizer.process_table(table_dict)
+
+# add question
+question = "how many movies does George Clooney have?"
+joint_input = question + " " + linear_table
+
+# encode 
+encoding = tokenizer(joint_input, return_tensors="pt")
+
+# forward pass
+outputs = model.generate(**encoding)
+
+# decode
+tokenizer.batch_decode(outputs, skip_special_tokens=True)