v0.2: 4M, made from cbx-pii-extractor-17M v0.2 (16K vocab, compressed word table, 4 layers, 68M teacher)
c57104c verified | { | |
| "backend": "tokenizers", | |
| "clean_up_tokenization_spaces": true, | |
| "cls_token": "[CLS]", | |
| "is_local": true, | |
| "local_files_only": false, | |
| "mask_token": "[MASK]", | |
| "model_input_names": [ | |
| "input_ids", | |
| "attention_mask" | |
| ], | |
| "model_max_length": 8192, | |
| "pad_token": "[PAD]", | |
| "sep_token": "[SEP]", | |
| "tokenizer_class": "TokenizersBackend", | |
| "unk_token": "[UNK]" | |
| } | |