colbertv2.0 / tokenizer_config.json
okhattab's picture
First commit
0855eac
raw
history blame contribute delete
405 Bytes
{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "/future/u/okhattab/root/unit/experiments/2021.10/none/kld.v3.nway32.l2.ib/checkpoints/colbert-150000/", "tokenizer_class": "BertTokenizer"}