v0.2.1: TinyBERT address autofill, no-** retrain (k6bxl, jt4qd's EXACT train/val/test (apples-to-apples with the v2 jt4qd run))
f06031d verified | { | |
| "added_tokens_decoder": { | |
| "0": { | |
| "content": "[PAD]", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "100": { | |
| "content": "[UNK]", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "101": { | |
| "content": "[CLS]", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "102": { | |
| "content": "[SEP]", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "103": { | |
| "content": "[MASK]", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| } | |
| }, | |
| "backend": "tokenizers", | |
| "clean_up_tokenization_spaces": false, | |
| "cls_token": "[CLS]", | |
| "do_lower_case": true, | |
| "extra_special_tokens": {}, | |
| "is_local": false, | |
| "local_files_only": false, | |
| "mask_token": "[MASK]", | |
| "max_length": 512, | |
| "model_max_length": 1000000000000000019884624838656, | |
| "pad_token": "[PAD]", | |
| "sep_token": "[SEP]", | |
| "stride": 0, | |
| "strip_accents": null, | |
| "tokenize_chinese_chars": true, | |
| "tokenizer_class": "BertTokenizer", | |
| "truncation_side": "right", | |
| "truncation_strategy": "longest_first", | |
| "unk_token": "[UNK]" | |
| } | |