paraphrase-MiniLM-L12-v2-CoLA / tokenizer_config.json
pszemraj's picture
Training in progress, epoch 1
a9b13db
raw
history blame
595 Bytes
{
"cls_token": "[CLS]",
"do_basic_tokenize": true,
"do_lower_case": true,
"mask_token": "[MASK]",
"model_max_length": 512,
"name_or_path": "sentence-transformers/paraphrase-MiniLM-L12-v2",
"never_split": null,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"special_tokens_map_file": "/home/pszemraj/.cache/huggingface/hub/models--sentence-transformers--paraphrase-MiniLM-L12-v2/snapshots/8f010f24d5c0e1ee9735f056d024fcda6557f70f/special_tokens_map.json",
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "BertTokenizer",
"unk_token": "[UNK]"
}