Lilt Document QA

🚀 LiLT文档问答模型

LiLT模型是用于文档问答任务的模型，本模型在英文DocVQA数据集上进行了微调，能有效处理文档相关的问答需求。

🚀 快速开始

你可以按照以下步骤使用LiLT模型进行文档问答：

from transformers import AutoTokenizer, AutoModelForQuestionAnswering
from datasets import load_dataset

model_checkpoint = "TusharGoel/LiLT-Document-QA"
tokenizer = AutoTokenizer.from_pretrained(model_checkpoint, add_prefix_space=True)
model_predict = AutoModelForQuestionAnswering.from_pretrained(model_checkpoint)

model_predict.eval()
dataset = load_dataset("nielsr/funsd", split="train")
example = dataset[0]
print(example)

question = "What is the Licensee Number?"
print(question)

words = example["words"]
boxes = example["bboxes"]

encoding = tokenizer(question, words, boxes = boxes, return_token_type_ids=True, return_tensors="pt")

word_ids = encoding.word_ids(0)
outputs = model_predict(**encoding)

loss = outputs.loss
start_scores = outputs.start_logits
end_scores = outputs.end_logits

start, end = word_ids[start_scores.argmax(-1).item()], word_ids[end_scores.argmax(-1).item()]
# print(start, end)
print(" ".join(words[start : end + 1]))

💻 使用示例

基础用法

from transformers import AutoTokenizer, AutoModelForQuestionAnswering
from datasets import load_dataset

model_checkpoint = "TusharGoel/LiLT-Document-QA"
tokenizer = AutoTokenizer.from_pretrained(model_checkpoint, add_prefix_space=True)
model_predict = AutoModelForQuestionAnswering.from_pretrained(model_checkpoint)

model_predict.eval()
dataset = load_dataset("nielsr/funsd", split="train")
example = dataset[0]
print(example)

question = "What is the Licensee Number?"
print(question)

words = example["words"]
boxes = example["bboxes"]

encoding = tokenizer(question, words, boxes = boxes, return_token_type_ids=True, return_tensors="pt")

word_ids = encoding.word_ids(0)
outputs = model_predict(**encoding)

loss = outputs.loss
start_scores = outputs.start_logits
end_scores = outputs.end_logits

start, end = word_ids[start_scores.argmax(-1).item()], word_ids[end_scores.argmax(-1).item()]
# print(start, end)
print(" ".join(words[start : end + 1]))

📄 许可证

本项目采用MIT许可证。

📚 详细文档

LiLT模型的详细信息请点击此处查看。