File size: 788 Bytes
5fa1a76 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 |
thon
from transformers import AutoTokenizer, AutoModelForSequenceClassification
tokenizer = AutoTokenizer.from_pretrained("microsoft/tapex-large-finetuned-tabfact")
model = AutoModelForSequenceClassification.from_pretrained("microsoft/tapex-large-finetuned-tabfact")
prepare table + sentence
data = {"Actors": ["Brad Pitt", "Leonardo Di Caprio", "George Clooney"], "Number of movies": ["87", "53", "69"]}
table = pd.DataFrame.from_dict(data)
sentence = "George Clooney has 30 movies"
encoding = tokenizer(table, sentence, return_tensors="pt")
forward pass
outputs = model(**encoding)
print prediction
predicted_class_idx = outputs.logits[0].argmax(dim=0).item()
print(model.config.id2label[predicted_class_idx])
Refused
TAPEX architecture is the same as BART, except for tokenization. |