File size: 1,589 Bytes
9855500 7f0f462 9855500 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 |
---
language: en
tags:
- tapex
license: apache-2.0
datasets:
- tab_fact
inference: false
---
TAPEX-large model fine-tuned on WTQ. This model was proposed in [TAPEX: Table Pre-training via Learning a Neural SQL Executor](https://arxiv.org/abs/2107.07653) by Qian Liu, Bei Chen, Jiaqi Guo, Morteza Ziyadi, Zeqi Lin, Weizhu Chen, Jian-Guang Lou. Original repo can be found [here](https://github.com/microsoft/Table-Pretraining).
To load it and run inference, you can do the following:
```
from transformers import BartTokenizer, BartForSequenceClassification
import pandas as pd
tokenizer = BartTokenizer.from_pretrained("nielsr/tapex-large-finetuned-tabfact")
model = BartForSequenceClassification.from_pretrained("nielsr/tapex-large-finetuned-tabfact")
# 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 sentence
sentence = "George Clooney has 69 movies"
joint_input = sentence + " " + linear_table
# encode
encoding = tokenizer(joint_input, return_tensors="pt")
# forward pass
outputs = model(**encoding)
# print prediction
logits = outputs.logits
print(logits.argmax(-1))
``` |