| import transformers | |
| import os | |
| import torch | |
| MAX_LEN = 150 #256 | |
| TRAIN_BATCH_SIZE = 8 | |
| VALID_BATCH_SIZE = 4 | |
| EPOCHS = 5 | |
| # Folder to contain all the datasets | |
| DATASET_LOCATION = "" # | |
| MODEL_PATH = "https://huggingface.co/thak123/bert-emoji-latvian-twitter-classifier/resolve/main/model.bin" | |
| device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') | |
| # 7 EPOCH Version | |
| BERT_PATH = "FFZG-cleopatra/bert-emoji-latvian-twitter" | |
| # TODO check if lower casing is required | |
| # BertTokenizer | |
| TOKENIZER = transformers.BertTokenizer.from_pretrained( | |
| BERT_PATH, | |
| do_lower_case=True | |
| ) | |
| #################################################################################################################################### | |