| import numpy as np | |
| import pandas as pd | |
| import seaborn as sns | |
| from typing import Optional, List, Tuple, Any | |
| from collections import OrderedDict | |
| import os | |
| import ast | |
| import re | |
| import string | |
| from sklearn.preprocessing import MultiLabelBinarizer, LabelEncoder | |
| import torch | |
| from torch.utils.data import Dataset, DataLoader | |
| from sklearn.model_selection import train_test_split | |
| import datasets | |
| import transformers | |
| from transformers import AutoTokenizer, AutoModel, AutoModelForSequenceClassification, Trainer, TrainingArguments, logging, RobertaForTokenClassification, RobertaConfig, AutoConfig | |
| from torch.nn.utils.rnn import pack_padded_sequence, pad_packed_sequence | |
| from torchcrf import CRF | |
| from accelerate import Accelerator | |
| import torch.nn as nn | |
| import torch.nn.functional as F | |
| import underthesea | |
| from utils import * | |
| from all_datasets import * | |
| from model import * | |
| from huggingface_hub import login | |
| import PIL, fitz, pdf2image, re, unicodedata | |
| from transformers import AutoProcessor, LayoutLMv3ForTokenClassification | |
| from unidecode import unidecode |